pytorch - ✅(Solved) Fix [pipelining] PP fails when trying to pipeline any HF transformers model that uses RoPE [3 pull requests, 1 comments, 1 participants]
ON THIS PAGE
Recommended Tools
×6Utilities matched from this issue’s tags and category — try them while you read without losing context.
GitHub issue graph ai analysis
Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.
The report is written in English Markdown for sharing and archival.
Helpful · Quick feedback
GitHub stats
pytorch/pytorch#184361•Fetched 2026-05-20 03:39:07
Comments
1
Participants
1
Timeline
30
Reactions
0
Author
fffffgggg54Participants
Timeline (top)
mentioned ×12subscribed ×12labeled ×5commented ×1
Error Message
(pt) fyguan@beast:~/disk20$ torchrun --nproc-per-node 2 pipelining_model_backward.py
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851]
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851] *****************************************
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851] *****************************************
[Rank 1] Starting model init on cuda:1
[Rank 0] Starting model init on cuda:0
Loading weights: 100%|████████████████████████████████████████████████████████████████████████████████████████████| 272/272 [00:00<00:00, 41777.16it/s]
Loading weights: 100%|████████████████████████████████████████████████████████████████████████████████████████████| 272/272 [00:00<00:00, 38255.34it/s]
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(49152, 576)
(layers): ModuleList(
(0-29): 30 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=576, out_features=576, bias=False)
(k_proj): Linear(in_features=576, out_features=192, bias=False)
(v_proj): Linear(in_features=576, out_features=192, bias=False)
(o_proj): Linear(in_features=576, out_features=576, bias=False)
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=576, out_features=1536, bias=False)
(up_proj): Linear(in_features=576, out_features=1536, bias=False)
(down_proj): Linear(in_features=1536, out_features=576, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm((576,), eps=1e-05)
(post_attention_layernorm): LlamaRMSNorm((576,), eps=1e-05)
)
)
(norm): LlamaRMSNorm((576,), eps=1e-05)
(rotary_emb): LlamaRotaryEmbedding()
)
(lm_head): Linear(in_features=576, out_features=49152, bias=False)
)
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(49152, 576)
(layers): ModuleList(
(0-29): 30 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=576, out_features=576, bias=False)
(k_proj): Linear(in_features=576, out_features=192, bias=False)
(v_proj): Linear(in_features=576, out_features=192, bias=False)
(o_proj): Linear(in_features=576, out_features=576, bias=False)
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=576, out_features=1536, bias=False)
(up_proj): Linear(in_features=576, out_features=1536, bias=False)
(down_proj): Linear(in_features=1536, out_features=576, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm((576,), eps=1e-05)
(post_attention_layernorm): LlamaRMSNorm((576,), eps=1e-05)
)
)
(norm): LlamaRMSNorm((576,), eps=1e-05)
(rotary_emb): LlamaRotaryEmbedding()
)
(lm_head): Linear(in_features=576, out_features=49152, bias=False)
)
/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/copyreg.py:99: FutureWarning: isinstance(treespec, LeafSpec) is deprecated, use isinstance(treespec, TreeSpec) and treespec.is_leaf() instead.
return cls.new(cls, *args)
/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/copyreg.py:99: FutureWarning: isinstance(treespec, LeafSpec) is deprecated, use isinstance(treespec, TreeSpec) and treespec.is_leaf() instead.
return cls.new(cls, *args)
[rank0]: Traceback (most recent call last):
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 328, in placeholder
[rank0]: return next(self.args_iter)
[rank0]: ^^^^^^^^^^^^^^^^^^^^
[rank0]: StopIteration
[rank0]: The above exception was the direct cause of the following exception:
[rank0]: Traceback (most recent call last): [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/stage.py", line 892, in forward_one_chunk [rank0]: output = self.forward_maybe_with_nosync(*composite_args, **composite_kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/stage.py", line 762, in forward_maybe_with_nosync [rank0]: out_val = self.submod(*args, **kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/graph_module.py", line 949, in call_wrapped [rank0]: return self._wrapped_call(self, *args, **kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/graph_module.py", line 461, in call [rank0]: raise e [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/graph_module.py", line 447, in call [rank0]: return super(self.cls, obj).call(*args, **kwargs) # type: ignore[misc] [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [rank0]: return self._call_impl(*args, **kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [rank0]: return forward_call(*args, **kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "<eval_with_key>.474", line 6, in forward [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [rank0]: return self._call_impl(*args, **kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [rank0]: return forward_call(*args, **kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/export/unflatten.py", line 216, in forward [rank0]: return torch.fx.Interpreter(self, graph=self.graph).run( [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 200, in run [rank0]: self.env[node] = self.run_node(node) [rank0]: ^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 297, in run_node [rank0]: return getattr(self, n.op)(n.target, args, kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 431, in call_module [rank0]: return submod(*args, **kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl [rank0]: return self._call_impl(*args, **kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl [rank0]: return forward_call(*args, **kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/export/unflatten.py", line 216, in forward [rank0]: return torch.fx.Interpreter(self, graph=self.graph).run( [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 200, in run [rank0]: self.env[node] = self.run_node(node) [rank0]: ^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 297, in run_node [rank0]: return getattr(self, n.op)(n.target, args, kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 333, in placeholder [rank0]: raise RuntimeError( [rank0]: RuntimeError: Expected positional argument for parameter unsqueeze_default, but one was not passed in!
[rank0]: While executing %unsqueeze_default : [num_users=1] = placeholder[target=unsqueeze_default] [rank0]: Original traceback: [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/transformers/models/llama/modeling_llama.py", line 474, in forward [rank0]: outputs: BaseModelOutputWithPast = self.model( [rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/transformers/models/llama/modeling_llama.py", line 397, in forward [rank0]: position_ids = position_ids.unsqueeze(0) [rank0]: Use tlparse to see full graph. (https://github.com/pytorch/tlparse?tab=readme-ov-file#tlparse-parse-structured-pt2-logs)
[rank0]: While executing %rotary_emb : [num_users=1] = call_module[target=rotary_emb](args = (), kwargs = {}) [rank0]: Original traceback: [rank0]: None [rank0]: Use tlparse to see full graph. (https://github.com/pytorch/tlparse?tab=readme-ov-file#tlparse-parse-structured-pt2-logs)
[rank0]: The above exception was the direct cause of the following exception:
[rank0]: Traceback (most recent call last):
[rank0]: File "/mnt/disk20/user/fyguan/pipelining_model_backward.py", line 79, in <module>
[rank0]: schedule.step(
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/schedules.py", line 604, in step
[rank0]: self._step_microbatches(
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/schedules.py", line 873, in _step_microbatches
[rank0]: output = self._stage.forward_one_chunk(
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/stage.py", line 900, in forward_one_chunk
[rank0]: raise RuntimeError(exc_msg) from e
[rank0]: RuntimeError:
[rank0]: [Stage 0] failed to run forward:
[rank0]: args: ()
[rank0]: kwargs: {'input_ids': 'Tensor(torch.Size([1, 512]), grad=False, dtype=torch.int64)', 'attention_mask': 'Tensor(torch.Size([1, 512]), grad=False, dtype=torch.bool)'}
[rank0]:
[rank0]:[W519 11:42:51.791357236 ProcessGroupNCCL.cpp:1575] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
W0519 11:42:54.151000 53989 site-packages/torch/distributed/elastic/multiprocessing/api.py:1012] Sending process 54075 closing signal SIGTERM
E0519 11:42:54.469000 53989 site-packages/torch/distributed/elastic/multiprocessing/api.py:986] failed (exitcode: 1) local_rank: 0 (pid: 54074) of binary: /mnt/disk20/user/fyguan/miniconda3/envs/pt/bin/python3.12
Traceback (most recent call last):
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/bin/torchrun", line 6, in <module>
sys.exit(main())
^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 362, in wrapper
return f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/run.py", line 990, in main
run(args)
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/run.py", line 981, in run
elastic_launch(
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 170, in call
return launch_agent(self._config, self._entrypoint, list(args))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 317, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
pipelining_model_backward.py FAILED
Failures: [1]: time : 2026-05-19_11:42:54 host : beast rank : 1 (local_rank: 1) exitcode : -15 (pid: 54075) error_file: <N/A> traceback : Signal 15 (SIGTERM) received by PID 54075
Root Cause (first observed failure): [0]: time : 2026-05-19_11:42:54 host : beast rank : 0 (local_rank: 0) exitcode : 1 (pid: 54074) error_file: <N/A> traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
Root Cause
[rank0]: Traceback (most recent call last):
[rank0]: File "/mnt/disk20/user/fyguan/pipelining_model_backward.py", line 79, in <module>
[rank0]: schedule.step(
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/schedules.py", line 604, in step
[rank0]: self._step_microbatches(
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/schedules.py", line 873, in _step_microbatches
[rank0]: output = self._stage.forward_one_chunk(
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/stage.py", line 900, in forward_one_chunk
[rank0]: raise RuntimeError(exc_msg) from e
[rank0]: RuntimeError:
[rank0]: [Stage 0] failed to run forward:
[rank0]: args: ()
[rank0]: kwargs: {'input_ids': 'Tensor(torch.Size([1, 512]), grad=False, dtype=torch.int64)', 'attention_mask': 'Tensor(torch.Size([1, 512]), grad=False, dtype=torch.bool)'}
[rank0]:
[rank0]:[W519 11:42:51.791357236 ProcessGroupNCCL.cpp:1575] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
W0519 11:42:54.151000 53989 site-packages/torch/distributed/elastic/multiprocessing/api.py:1012] Sending process 54075 closing signal SIGTERM
E0519 11:42:54.469000 53989 site-packages/torch/distributed/elastic/multiprocessing/api.py:986] failed (exitcode: 1) local_rank: 0 (pid: 54074) of binary: /mnt/disk20/user/fyguan/miniconda3/envs/pt/bin/python3.12
Traceback (most recent call last):
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/bin/torchrun", line 6, in <module>
sys.exit(main())
^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 362, in wrapper
return f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/run.py", line 990, in main
run(args)
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/run.py", line 981, in run
elastic_launch(
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 170, in call
return launch_agent(self._config, self._entrypoint, list(args))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 317, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
pipelining_model_backward.py FAILED
Failures: [1]: time : 2026-05-19_11:42:54 host : beast rank : 1 (local_rank: 1) exitcode : -15 (pid: 54075) error_file: <N/A> traceback : Signal 15 (SIGTERM) received by PID 54075
Root Cause (first observed failure): [0]: time : 2026-05-19_11:42:54 host : beast rank : 0 (local_rank: 0) exitcode : 1 (pid: 54074) error_file: <N/A> traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
Fix Action
Fix / Workaround
CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 52 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 256 On-line CPU(s) list: 0-255 Vendor ID: AuthenticAMD Model name: AMD EPYC 9555 64-Core Processor CPU family: 26 Model: 2 Thread(s) per core: 2 Core(s) per socket: 64 Socket(s): 2 Stepping: 1 Frequency boost: enabled CPU(s) scaling MHz: 84% CPU max MHz: 4410.8110 CPU min MHz: 1210.8110 BogoMIPS: 6391.45 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpuid_fault cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 invpcid cqm rdt_a avx512f avx512dq adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx_vnni avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect movdiri movdir64b overflow_recov succor smca avx512_vp2intersect flush_l1d debug_swap amd_lbr_pmc_freeze Virtualization: AMD-V L1d cache: 6 MiB (128 instances) L1i cache: 4 MiB (128 instances) L2 cache: 128 MiB (128 instances) L3 cache: 512 MiB (16 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-63,128-191 NUMA node1 CPU(s): 64-127,192-255 Vulnerability Gather data sampling: Not affected Vulnerability Ghostwrite: Not affected Vulnerability Indirect target selection: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Old microcode: Not affected Vulnerability Reg file data sampling: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Mitigation; Reduced Speculation Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; STIBP always-on; PBRSB-eIBRS Not affected; BHI Not affected Vulnerability Srbds: Not affected Vulnerability Tsa: Not affected Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Mitigation; IBPB before exit to userspace
PR fix notes
PR #182182: [pipelining] Fix None gradient handling in backward send/recv
- Repository: pytorch/pytorch
- Author: sanketpurandare
- State: open | merged: False
- Link: https://github.com/pytorch/pytorch/pull/182182
Description (problem / solution / changelog)
Pipeline backward metadata now allocates gradient recv buffers conservatively for differentiable plain tensors, so later microbatches can send real gradients even when the inference microbatch produced None. DTensor gradient metadata is not invented from activation metadata; if inference records None and runtime later produces a DTensor gradient, runtime errors instead of silently dropping or guessing its placement.
Runtime backward sends now key off metadata allocation: they send real gradients when available, send zeros when metadata captured a grad slot but runtime returns None, and error when a real gradient appears with no recv buffer allocated.
This also aligns split input-backward with full backward by filtering non-differentiable outputs before autograd.grad and allowing unused inputs, which is needed by ZBV-style schedules when a microbatch has no boundary input gradient. The old verbose stage-only tests were replaced with concise schedule coverage for GPipe, Interleaved1F1B, and ZBV over both mismatch directions, plus DTensor unit coverage for the no-implicit-metadata runtime contract.
Fixes https://github.com/pytorch/pytorch/issues/152827 Fixes https://github.com/pytorch/torchtitan/issues/2748
Authored with Codex.
Changed files
test/distributed/pipelining/model_registry.py(modified, +32/-0)test/distributed/pipelining/test_dtensor_pp_unit_tests.py(modified, +54/-0)test/distributed/pipelining/test_schedule_multiproc.py(modified, +109/-1)torch/distributed/pipelining/_backward.py(modified, +21/-13)torch/distributed/pipelining/_utils.py(modified, +15/-7)torch/distributed/pipelining/stage.py(modified, +74/-12)
PR #182644: Fix pipelining crash when split_module interleaves get_attr with placeholder
- Repository: pytorch/pytorch
- Author: arkadip-maitra
- State: closed | merged: False
- Link: https://github.com/pytorch/pytorch/pull/182644
Description (problem / solution / changelog)
Fixes #162898
split_module can produce partition subgraphs where get_attr nodes are interleaved with placeholder nodes. _ModuleFrame.run_outer() assumes placeholders form a contiguous prefix, so it crashes when this invariant is violated.
added _move_placeholders_to_front to reorder the graph before _outline_submodules runs and added tests.
also verified with the actual SmolLM2 model from the issue
Changed files
test/distributed/pipelining/test_unflatten.py(modified, +51/-0)torch/distributed/pipelining/_IR.py(modified, +22/-0)
PR #183582: [pipelining] Add guards for non-float tensors when building pipeline
- Repository: pytorch/pytorch
- Author: fffffgggg54
- State: open | merged: False
- Link: https://github.com/pytorch/pytorch/pull/183582
Description (problem / solution / changelog)
Fixes #183024. Tested working with code below by manually applying the patch over 2.11. Analysis and initial patches found using AI. Manually applied and tested patches.
<details> <summary> Test code, run with torchrun on 2 gpus </summary>import torch
import torch.distributed as dist
from torch.distributed.pipelining import pipeline, SplitPoint, PipelineStage, Schedule1F1B
from transformers import AutoModelForCausalLM
import os
# Initialize torchrun's distributed environment
pp_group = dist.init_process_group(backend="nccl")
rank = dist.get_rank()
world_size = dist.get_world_size()
local_rank = int(os.environ["LOCAL_RANK"])
# Assign this specific process to its designated GPU
device = torch.device(f"cuda:{local_rank}")
torch.cuda.set_device(device)
print(f"[Rank {rank}] Starting model init on {device}")
# GPT2
model_id = "openai-community/gpt2"
device_count = torch.cuda.device_count()
model = AutoModelForCausalLM.from_pretrained(model_id)
print(model)
# kv cache is enabled by default and causes other issues with dynamo tracing/pipelining, disabling
model.config.use_cache = False
# run on 2 or more gpus
split_spec = {
f"transformer.h.5": SplitPoint.END,
}
model = model.to(device)
pipe_module = pipeline(
module=model,
mb_args=(),
mb_kwargs={
'input_ids': torch.zeros((1, 512), dtype=torch.long).to(device),
'attention_mask': torch.ones((1, 512), dtype=torch.bool).to(device)
},
split_spec=split_spec,
)
stage = pipe_module.build_stage(rank, device, pp_group)
# placeholder loss function
def loss_fn(outputs, other):
if isinstance(outputs, tuple):
return outputs[0]
elif isinstance(outputs, torch.Tensor):
logits = outputs
else:
logits = outputs['logits']
loss = logits.sum() - other.sum()
return loss
schedule = Schedule1F1B(stage, n_microbatches=4, loss_fn=loss_fn)
if rank == 0:
inputs = {
'input_ids': torch.zeros((4, 512), dtype=torch.long).to(device),
'attention_mask': torch.ones((4, 512), dtype=torch.bool).to(device),
}
schedule.step(
**inputs
)
elif rank == world_size - 1:
losses = []
output = schedule.step(target=torch.randn(4, 512).to(device), losses=losses)
print(f"losses: {losses}")
else:
schedule.step()Prompt:
Analyze, triage, and provide me with a fix for this github issue
https://github.com/pytorch/pytorch/issues/183024
Z.ai agent response:
I'll analyze this GitHub issue for you. Let me start by fetching the issue details and understanding the problem. Let me extract the actual issue content more cleanly. Now let me look at the PyTorch source code for the specific failing function to understand the bug deeply. Now I have a complete picture. Let me also verify the related backward code path to ensure the fix is comprehensive. I now have a comprehensive understanding of the issue. Here's my full analysis, triage, and proposed fix:
🔍 Issue Analysis: PyTorch #183024
Title: [pipelining] Unable to use PP with HF transformers models due to non-float inputs
Bug Summary
When using PyTorch's Pipeline Parallelism (torch.distributed.pipelining) with HuggingFace transformer models (GPT2, LLaMA, etc.), the pipeline crashes with:
RuntimeError: only Tensors of floating point dtype can require gradients🧬 Root Cause
The root cause is a dtype-agnostic requires_grad assignment in the pipeline stage infrastructure. When has_backward=True (training mode), the code unconditionally sets requires_grad=True on all activation receive/send buffers — including non-float tensors like input_ids (torch.long) and attention_mask (torch.bool). PyTorch only allows floating-point tensors to require gradients (a fundamental constraint since Issue #37680, open since 2020).
The crash occurs at three specific locations:
Location 1: torch/distributed/pipelining/stage.py — create_recv_tensor inside _create_act_recv_info (PRIMARY CRASH)
# Lines ~1361-1377 (broken)
tensor_meta = _TensorMeta(
shape=example_value.shape,
stride=example_value.stride(),
dtype=example_value.dtype,
requires_grad=self.has_backward, # ← BUG: True for ALL dtypes
)
buffer = _make_tensor_from_meta(tensor_meta, self.device)
if self.has_backward:
buffer.requires_grad_(True) # ← CRASH: non-float tensors can't require gradThis is the exact crash point from the traceback. When the pipeline creates receive buffers for intermediate activations between stages, it encounters input_ids (dtype=torch.long) or attention_mask (dtype=torch.bool) and tries to set requires_grad_(True), which is illegal.
Location 2: torch/distributed/pipelining/stage.py — _create_act_send_info (SECONDARY)
# Lines ~1462-1468 (broken)
output_metas.append(
_TensorMeta(
shape=val.shape,
stride=val.stride(),
dtype=val.dtype,
requires_grad=self.has_backward, # ← Same bug for outputs
)
)Location 3: torch/distributed/pipelining/_utils.py — _TensorMeta.to_tensor (LATENT)
# Line ~96 (broken)
t = _make_tensor_from_meta(self, device)
t.requires_grad_(self.requires_grad) # ← Crashes if requires_grad=True and dtype is non-float
return tAdditional Related Bug: torch/distributed/pipelining/_backward.py — _get_grad_fn_or_grad_acc
Even after fixing the above, the backward pass has a second bug waiting to surface. The function _get_grad_fn_or_grad_acc assumes its argument is always a torch.Tensor:
def _get_grad_fn_or_grad_acc(t: torch.Tensor) -> Node | None:
if t.requires_grad and t.grad_fn is None: # ← AttributeError if t is not a Tensor
...This is called via map(_get_grad_fn_or_grad_acc, input_values) in stage_backward_input, where input_values can contain non-tensor objects. While the immediate crash is masked by Location 1, once that's fixed, this will be the next crash site.
🔧 Proposed Fix
The fix is to guard requires_grad=True with a tensor.is_floating_point() check at all affected locations. This is semantically correct because:
- Non-float tensors (integer, boolean) never produce meaningful gradients
- Their gradient in the backward pass should be
None - This is consistent with PyTorch's autograd semantics
Patch 1: torch/distributed/pipelining/stage.py — create_recv_tensor
def create_recv_tensor(placeholder, arg_node):
example_value = placeholder.meta["val"]
# ... (DTensor check unchanged) ...
if arg_node.op == "placeholder":
return _RecvInfo(
input_name=f"root_input_{placeholder.name}",
source=None,
buffer=None,
tensor_meta=_TensorMeta.from_tensor(example_value),
is_root_arg=True,
)
# Received activation from a previous stage.
while arg_node.target is operator.getitem:
arg_node = arg_node.args[0]
if arg_node.op != "call_module":
raise PipeliningMetadataError(
f"Expecting call_module, got {arg_node.op}"
)
src_stage = self.get_stage_index_of_submod(arg_node.name)
# FIX: Only set requires_grad for floating-point tensors
needs_grad = self.has_backward and example_value.is_floating_point()
tensor_meta = _TensorMeta(
shape=example_value.shape,
stride=example_value.stride(),
dtype=example_value.dtype,
requires_grad=needs_grad, # ← was: self.has_backward
)
buffer = _make_tensor_from_meta(tensor_meta, self.device)
if needs_grad: # ← was: if self.has_backward
buffer.requires_grad_(True)
return _RecvInfo(
arg_node.name,
src_stage,
buffer,
tensor_meta,
)Patch 2: torch/distributed/pipelining/stage.py — _create_act_send_info
# Inside _create_act_send_info, where output_metas are built:
output_metas.append(
_TensorMeta(
shape=val.shape,
stride=val.stride(),
dtype=val.dtype,
requires_grad=self.has_backward and val.is_floating_point(), # ← was: self.has_backward
)
)Patch 3: torch/distributed/pipelining/_utils.py — _TensorMeta.to_tensor
def to_tensor(self, device: torch.device | str) -> torch.Tensor:
t = _make_tensor_from_meta(self, device)
if self.requires_grad and t.is_floating_point(): # ← was: unconditionally
t.requires_grad_(True)
return tPatch 4: torch/distributed/pipelining/_backward.py — _get_grad_fn_or_grad_acc
def _get_grad_fn_or_grad_acc(t: torch.Tensor) -> Node | None:
# FIX: Guard against non-tensor inputs
if not isinstance(t, torch.Tensor):
return None
if t.requires_grad and t.grad_fn is None:
viewed_t = t.view_as(t)
grad_fn = viewed_t.grad_fn
if grad_fn is not None:
return grad_fn.next_functions[0][0]
else:
raise RuntimeError(
"Attempted to get grad_fn, but got None."
"Is this being created in a no-grad context?"
)
else:
return t.grad_fn📊 Triage Assessment
| Aspect | Rating |
|---|---|
| Severity | 🔴 High — Completely blocks pipeline parallelism for any model with non-float inputs (all HF transformer models) |
| Impact | 🔴 High — Affects GPT2, LLaMA, BERT, T5 — essentially all popular transformer architectures |
| Workaround? | 🟡 Difficult — Would require rewriting models to avoid passing non-float tensors between stages, or monkey-patching the pipelining internals |
| Fix Complexity | 🟢 Low — Four surgical is_floating_point() / isinstance guards, no architectural changes |
| Regression Risk | 🟢 Low — The fix only restricts requires_grad for cases that already crash; float tensors are unaffected |
Why PRs #182182 and #182644 Don't Fix This
- PR #182182 fixes None gradient handling for float tensors that are unused — it doesn't address the dtype mismatch
- PR #182644 fixes FX graph node ordering — it doesn't touch the
requires_gradlogic at all - This is a distinct, orthogonal bug that needs its own fix
🚀 Suggested Next Steps
- File a PR against
pytorch/pytorchwith the four patches above - Add regression tests that pipeline an HF model (even a tiny one like GPT2-small) with
input_idsandattention_mask - Coordinate with PR #182182 — both fixes are needed for full pipeline parallelism support, and they should be tested together since they both touch the backward path
Prompt:
Check your work
Z.ai agent response:
Good call — let me verify my analysis against the actual PyTorch source code. I'll cross-check each claim.
Now I have verified all the source code against my original analysis. Let me also check one more thing — whether the to_tensor method is actually called in the crash path or not.
Now let me verify the secondary bug claim about _get_grad_fn_or_grad_acc — whether it would actually be hit in the backward path after fixing the primary bug.
Good — my verification is complete. Here's the corrected and refined analysis:
✅ Verification Results
Claims Confirmed ✅
| Claim | Status | Evidence |
|---|---|---|
Primary crash: create_recv_tensor sets requires_grad=self.has_backward unconditionally | ✅ Confirmed | Exact match with source at stage.py lines ~1361-1377 |
Primary crash: buffer.requires_grad_(True) when self.has_backward | ✅ Confirmed | Line ~1377, crashes for torch.long/torch.bool tensors |
Secondary bug: _create_act_send_info uses same requires_grad=self.has_backward pattern | ✅ Confirmed | Line ~1467, same unconditional pattern for outputs |
Latent bug: _TensorMeta.to_tensor() calls t.requires_grad_(self.requires_grad) unconditionally | ✅ Confirmed | _utils.py line ~96, same crash pattern |
| PR #182182 does NOT fix this | ✅ Confirmed | It fixes None gradient handling for float tensors, not the dtype mismatch |
| PR #182644 does NOT fix this | ✅ Confirmed | It fixes FX graph node ordering, doesn't touch requires_grad logic |
is_floating_point() guard is the correct fix | ✅ Confirmed | Semantically correct: non-float tensors can never produce meaningful gradients in PyTorch |
Claim Clarified ⚠️
| Claim | Status | Correction |
|---|---|---|
_get_grad_fn_or_grad_acc will crash next after the primary fix | ⚠️ Partially correct | This IS a real bug, but it's for a different scenario — when non-Tensor Python objects (int, bool, None) appear in input_values. In the HF GPT2 pipeline case specifically, input_values contains torch.Tensor objects (just non-float ones), which after the primary fix will have requires_grad=False and work fine. The isinstance guard is still a valid defense-in-depth fix but is not directly triggered by this issue. |
Revised Fix Assessment
Patch 1 (create_recv_tensor) — Essential, directly fixes the crash ✅
Patch 2 (_create_act_send_info) — Important, prevents same crash for non-float outputs crossing stage boundaries ✅
(Not triggered in GPT2 specifically since embedding outputs are float, but needed for models where non-float tensors cross stages)
Patch 3 (_TensorMeta.to_tensor) — Defensive, prevents latent crash if this method is called with requires_grad=True on non-float metadata ✅
Patch 4 (_get_grad_fn_or_grad_acc) — Separate bug, defense-in-depth ⚠️
Should be framed as a separate fix for the torchtitan #3112 scenario (non-Tensor Python objects in input_values), not as part of the immediate fix for issue #183024.
Bottom Line
My original analysis was substantially correct. The three core patches (1, 2, 3) are accurate and necessary. Patch 4 is a valid bug fix but should be presented as an orthogonal improvement rather than a direct consequence of fixing issue #183024. The root cause, severity assessment, and fix approach all hold up under verification.
</details>Changed files
torch/distributed/pipelining/_utils.py(modified, +2/-1)torch/distributed/pipelining/stage.py(modified, +4/-3)
Code Example
import torch
import torch.distributed as dist
from torch.distributed.pipelining import pipeline, SplitPoint, PipelineStage, Schedule1F1B
from transformers import AutoModelForCausalLM
import os
# Initialize torchrun's distributed environment
pp_group = dist.init_process_group(backend="nccl")
rank = dist.get_rank()
world_size = dist.get_world_size()
local_rank = int(os.environ["LOCAL_RANK"])
# Assign this specific process to its designated GPU
device = torch.device(f"cuda:{local_rank}")
torch.cuda.set_device(device)
print(f"[Rank {rank}] Starting model init on {device}")
#model_type = 'gpt2'
model_type = 'llama'
if model_type == 'gpt2':
# GPT2
model_id = "openai-community/gpt2"
elif model_type == 'llama':
# SmolLM (llama style, uses modeling_llama.py)
model_id = "HuggingFaceTB/SmolLM2-135M"
device_count = torch.cuda.device_count()
model = AutoModelForCausalLM.from_pretrained(model_id)
print(model)
# kv cache is enabled by default and causes other issues with dynamo tracing/pipelining, disabling
model.config.use_cache = False
# run on 2 or more gpus
if model_type == 'gpt2':
# GPT2
split_spec = {f"transformer.h.5": SplitPoint.END,}
elif model_type == 'llama':
# SmolLM/llama-style models
split_spec = {f"model.layers.14": SplitPoint.END,}
model = model.to(device)
pipe_module = pipeline(
module=model,
mb_args=(),
mb_kwargs={
'input_ids': torch.zeros((1, 512), dtype=torch.long).to(device),
'attention_mask': torch.ones((1, 512), dtype=torch.bool).to(device),
},
split_spec=split_spec,
)
stage = pipe_module.build_stage(rank, device, pp_group)
# placeholder loss function
def loss_fn(outputs, other):
if isinstance(outputs, tuple):
return outputs[0]
elif isinstance(outputs, torch.Tensor):
logits = outputs
else:
logits = outputs['logits']
loss = logits.sum() - other.sum()
return loss
schedule = Schedule1F1B(stage, n_microbatches=4, loss_fn=loss_fn)
if rank == 0:
inputs = {
'input_ids': torch.zeros((4, 512), dtype=torch.long).to(device),
'attention_mask': torch.ones((4, 512), dtype=torch.bool).to(device),
}
schedule.step(
**inputs,
)
elif rank == world_size - 1:
losses = []
output = schedule.step(target=torch.randn(4, 512).to(device), losses=losses)
print(f"losses: {losses}")
else:
schedule.step()
---
(pt) fyguan@beast:~/disk20$ torchrun --nproc-per-node 2 pipelining_model_backward.py
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851]
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851] *****************************************
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851] *****************************************
[Rank 1] Starting model init on cuda:1
[Rank 0] Starting model init on cuda:0
Loading weights: 100%|████████████████████████████████████████████████████████████████████████████████████████████| 272/272 [00:00<00:00, 41777.16it/s]
Loading weights: 100%|████████████████████████████████████████████████████████████████████████████████████████████| 272/272 [00:00<00:00, 38255.34it/s]
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(49152, 576)
(layers): ModuleList(
(0-29): 30 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=576, out_features=576, bias=False)
(k_proj): Linear(in_features=576, out_features=192, bias=False)
(v_proj): Linear(in_features=576, out_features=192, bias=False)
(o_proj): Linear(in_features=576, out_features=576, bias=False)
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=576, out_features=1536, bias=False)
(up_proj): Linear(in_features=576, out_features=1536, bias=False)
(down_proj): Linear(in_features=1536, out_features=576, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm((576,), eps=1e-05)
(post_attention_layernorm): LlamaRMSNorm((576,), eps=1e-05)
)
)
(norm): LlamaRMSNorm((576,), eps=1e-05)
(rotary_emb): LlamaRotaryEmbedding()
)
(lm_head): Linear(in_features=576, out_features=49152, bias=False)
)
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(49152, 576)
(layers): ModuleList(
(0-29): 30 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=576, out_features=576, bias=False)
(k_proj): Linear(in_features=576, out_features=192, bias=False)
(v_proj): Linear(in_features=576, out_features=192, bias=False)
(o_proj): Linear(in_features=576, out_features=576, bias=False)
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=576, out_features=1536, bias=False)
(up_proj): Linear(in_features=576, out_features=1536, bias=False)
(down_proj): Linear(in_features=1536, out_features=576, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm((576,), eps=1e-05)
(post_attention_layernorm): LlamaRMSNorm((576,), eps=1e-05)
)
)
(norm): LlamaRMSNorm((576,), eps=1e-05)
(rotary_emb): LlamaRotaryEmbedding()
)
(lm_head): Linear(in_features=576, out_features=49152, bias=False)
)
/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/copyreg.py:99: FutureWarning: `isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
return cls.__new__(cls, *args)
/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/copyreg.py:99: FutureWarning: `isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
return cls.__new__(cls, *args)
[rank0]: Traceback (most recent call last):
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 328, in placeholder
[rank0]: return next(self.args_iter)
[rank0]: ^^^^^^^^^^^^^^^^^^^^
[rank0]: StopIteration
[rank0]: The above exception was the direct cause of the following exception:
[rank0]: Traceback (most recent call last):
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/stage.py", line 892, in forward_one_chunk
[rank0]: output = self.forward_maybe_with_nosync(*composite_args, **composite_kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/stage.py", line 762, in forward_maybe_with_nosync
[rank0]: out_val = self.submod(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/graph_module.py", line 949, in call_wrapped
[rank0]: return self._wrapped_call(self, *args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/graph_module.py", line 461, in __call__
[rank0]: raise e
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/graph_module.py", line 447, in __call__
[rank0]: return super(self.cls, obj).__call__(*args, **kwargs) # type: ignore[misc]
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl
[rank0]: return forward_call(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "<eval_with_key>.474", line 6, in forward
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl
[rank0]: return forward_call(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/export/unflatten.py", line 216, in forward
[rank0]: return torch.fx.Interpreter(self, graph=self.graph).run(
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 200, in run
[rank0]: self.env[node] = self.run_node(node)
[rank0]: ^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 297, in run_node
[rank0]: return getattr(self, n.op)(n.target, args, kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 431, in call_module
[rank0]: return submod(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl
[rank0]: return forward_call(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/export/unflatten.py", line 216, in forward
[rank0]: return torch.fx.Interpreter(self, graph=self.graph).run(
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 200, in run
[rank0]: self.env[node] = self.run_node(node)
[rank0]: ^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 297, in run_node
[rank0]: return getattr(self, n.op)(n.target, args, kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 333, in placeholder
[rank0]: raise RuntimeError(
[rank0]: RuntimeError: Expected positional argument for parameter unsqueeze_default, but one was not passed in!
[rank0]: While executing %unsqueeze_default : [num_users=1] = placeholder[target=unsqueeze_default]
[rank0]: Original traceback:
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/transformers/models/llama/modeling_llama.py", line 474, in forward
[rank0]: outputs: BaseModelOutputWithPast = self.model(
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/transformers/models/llama/modeling_llama.py", line 397, in forward
[rank0]: position_ids = position_ids.unsqueeze(0)
[rank0]: Use tlparse to see full graph. (https://github.com/pytorch/tlparse?tab=readme-ov-file#tlparse-parse-structured-pt2-logs)
[rank0]: While executing %rotary_emb : [num_users=1] = call_module[target=rotary_emb](args = (), kwargs = {})
[rank0]: Original traceback:
[rank0]: None
[rank0]: Use tlparse to see full graph. (https://github.com/pytorch/tlparse?tab=readme-ov-file#tlparse-parse-structured-pt2-logs)
[rank0]: The above exception was the direct cause of the following exception:
[rank0]: Traceback (most recent call last):
[rank0]: File "/mnt/disk20/user/fyguan/pipelining_model_backward.py", line 79, in <module>
[rank0]: schedule.step(
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/schedules.py", line 604, in step
[rank0]: self._step_microbatches(
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/schedules.py", line 873, in _step_microbatches
[rank0]: output = self._stage.forward_one_chunk(
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/stage.py", line 900, in forward_one_chunk
[rank0]: raise RuntimeError(exc_msg) from e
[rank0]: RuntimeError:
[rank0]: [Stage 0] failed to run forward:
[rank0]: args: ()
[rank0]: kwargs: {'input_ids': 'Tensor(torch.Size([1, 512]), grad=False, dtype=torch.int64)', 'attention_mask': 'Tensor(torch.Size([1, 512]), grad=False, dtype=torch.bool)'}
[rank0]:
[rank0]:[W519 11:42:51.791357236 ProcessGroupNCCL.cpp:1575] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
W0519 11:42:54.151000 53989 site-packages/torch/distributed/elastic/multiprocessing/api.py:1012] Sending process 54075 closing signal SIGTERM
E0519 11:42:54.469000 53989 site-packages/torch/distributed/elastic/multiprocessing/api.py:986] failed (exitcode: 1) local_rank: 0 (pid: 54074) of binary: /mnt/disk20/user/fyguan/miniconda3/envs/pt/bin/python3.12
Traceback (most recent call last):
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/bin/torchrun", line 6, in <module>
sys.exit(main())
^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 362, in wrapper
return f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/run.py", line 990, in main
run(args)
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/run.py", line 981, in run
elastic_launch(
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 170, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 317, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
pipelining_model_backward.py FAILED
------------------------------------------------------------
Failures:
[1]:
time : 2026-05-19_11:42:54
host : beast
rank : 1 (local_rank: 1)
exitcode : -15 (pid: 54075)
error_file: <N/A>
traceback : Signal 15 (SIGTERM) received by PID 54075
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
time : 2026-05-19_11:42:54
host : beast
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 54074)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
============================================================
---
Collecting environment information...
PyTorch version: 2.11.0+cu130
Is debug build: False
CUDA used to build PyTorch: 13.0
ROCM used to build PyTorch: N/A
OS: Ubuntu 24.04.4 LTS (x86_64)
GCC version: (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version: Could not collect
CMake version: version 3.28.3
Libc version: glibc-2.39
Python version: 3.12.13 | packaged by conda-forge | (main, Mar 5 2026, 16:50:00) [GCC 14.3.0] (64-bit runtime)
Python platform: Linux-6.18.20-fyguan-x86_64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to:
GPU models and configuration:
GPU 0: NVIDIA H200 NVL
GPU 1: NVIDIA H200 NVL
GPU 2: NVIDIA H200 NVL
GPU 3: NVIDIA H200 NVL
Nvidia driver version: 590.48.01
cuDNN version: Could not collect
Is XPU available: False
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
Caching allocator config: N/A
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 52 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 256
On-line CPU(s) list: 0-255
Vendor ID: AuthenticAMD
Model name: AMD EPYC 9555 64-Core Processor
CPU family: 26
Model: 2
Thread(s) per core: 2
Core(s) per socket: 64
Socket(s): 2
Stepping: 1
Frequency boost: enabled
CPU(s) scaling MHz: 84%
CPU max MHz: 4410.8110
CPU min MHz: 1210.8110
BogoMIPS: 6391.45
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpuid_fault cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 invpcid cqm rdt_a avx512f avx512dq adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx_vnni avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect movdiri movdir64b overflow_recov succor smca avx512_vp2intersect flush_l1d debug_swap amd_lbr_pmc_freeze
Virtualization: AMD-V
L1d cache: 6 MiB (128 instances)
L1i cache: 4 MiB (128 instances)
L2 cache: 128 MiB (128 instances)
L3 cache: 512 MiB (16 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-63,128-191
NUMA node1 CPU(s): 64-127,192-255
Vulnerability Gather data sampling: Not affected
Vulnerability Ghostwrite: Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Old microcode: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Mitigation; Reduced Speculation
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; STIBP always-on; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsa: Not affected
Vulnerability Tsx async abort: Not affected
Vulnerability Vmscape: Mitigation; IBPB before exit to userspace
Versions of relevant libraries:
[pip3] numpy==2.4.3
[pip3] nvidia-cublas==13.1.0.3
[pip3] nvidia-cuda-cupti==13.0.85
[pip3] nvidia-cuda-nvrtc==13.0.88
[pip3] nvidia-cuda-runtime==13.0.96
[pip3] nvidia-cudnn-cu13==9.19.0.56
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-curand==10.4.0.35
[pip3] nvidia-cusolver==12.0.4.66
[pip3] nvidia-cusparse==12.6.3.3
[pip3] nvidia-cusparselt-cu13==0.8.0
[pip3] nvidia-nccl-cu13==2.28.9
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvtx==13.0.85
[pip3] torch==2.11.0+cu130
[pip3] torchaudio==2.11.0+cu130
[pip3] torchvision==0.26.0+cu130
[pip3] triton==3.6.0
[conda] cuda-nvrtc 13.2.51 hecca717_0 conda-forge
[conda] libcufft 12.2.0.37 hecca717_0 conda-forge
[conda] numpy 2.3.5 pypi_0 pypi
[conda] nvidia-cublas 13.1.0.3 pypi_0 pypi
[conda] nvidia-cuda-cupti 13.0.85 pypi_0 pypi
[conda] nvidia-cuda-nvrtc 13.0.88 pypi_0 pypi
[conda] nvidia-cuda-runtime 13.0.96 pypi_0 pypi
[conda] nvidia-cudnn-cu13 9.19.0.56 pypi_0 pypi
[conda] nvidia-cufft 12.0.0.61 pypi_0 pypi
[conda] nvidia-curand 10.4.0.35 pypi_0 pypi
[conda] nvidia-cusolver 12.0.4.66 pypi_0 pypi
[conda] nvidia-cusparse 12.6.3.3 pypi_0 pypi
[conda] nvidia-cusparselt-cu13 0.8.0 pypi_0 pypi
[conda] nvidia-nccl-cu13 2.28.9 pypi_0 pypi
[conda] nvidia-nvjitlink 13.0.88 pypi_0 pypi
[conda] nvidia-nvtx 13.0.85 pypi_0 pypi
[conda] torch 2.11.0+cu130 pypi_0 pypi
[conda] torchaudio 2.11.0+cu130 pypi_0 pypi
[conda] torchvision 0.26.0+cu130 pypi_0 pypi
[conda] triton 3.6.0 pypi_0 pypiRAW_BUFFERClick to expand / collapse
🐛 Describe the bug
Attempting to pipeline a HF transformers model that uses a llama-style RoPE impelementation (basically all post-2022 transformer-based causal LMs) results in RuntimeError: Expected positional argument for parameter unsqueeze_default, but one was not passed in!. Reproducing requires applying https://github.com/pytorch/pytorch/pull/182182, https://github.com/pytorch/pytorch/pull/182644, and https://github.com/pytorch/pytorch/pull/183582 over 2.11. The script runs successfully when model_type = 'gpt2' and fails when model_type = 'llama'.
import torch
import torch.distributed as dist
from torch.distributed.pipelining import pipeline, SplitPoint, PipelineStage, Schedule1F1B
from transformers import AutoModelForCausalLM
import os
# Initialize torchrun's distributed environment
pp_group = dist.init_process_group(backend="nccl")
rank = dist.get_rank()
world_size = dist.get_world_size()
local_rank = int(os.environ["LOCAL_RANK"])
# Assign this specific process to its designated GPU
device = torch.device(f"cuda:{local_rank}")
torch.cuda.set_device(device)
print(f"[Rank {rank}] Starting model init on {device}")
#model_type = 'gpt2'
model_type = 'llama'
if model_type == 'gpt2':
# GPT2
model_id = "openai-community/gpt2"
elif model_type == 'llama':
# SmolLM (llama style, uses modeling_llama.py)
model_id = "HuggingFaceTB/SmolLM2-135M"
device_count = torch.cuda.device_count()
model = AutoModelForCausalLM.from_pretrained(model_id)
print(model)
# kv cache is enabled by default and causes other issues with dynamo tracing/pipelining, disabling
model.config.use_cache = False
# run on 2 or more gpus
if model_type == 'gpt2':
# GPT2
split_spec = {f"transformer.h.5": SplitPoint.END,}
elif model_type == 'llama':
# SmolLM/llama-style models
split_spec = {f"model.layers.14": SplitPoint.END,}
model = model.to(device)
pipe_module = pipeline(
module=model,
mb_args=(),
mb_kwargs={
'input_ids': torch.zeros((1, 512), dtype=torch.long).to(device),
'attention_mask': torch.ones((1, 512), dtype=torch.bool).to(device),
},
split_spec=split_spec,
)
stage = pipe_module.build_stage(rank, device, pp_group)
# placeholder loss function
def loss_fn(outputs, other):
if isinstance(outputs, tuple):
return outputs[0]
elif isinstance(outputs, torch.Tensor):
logits = outputs
else:
logits = outputs['logits']
loss = logits.sum() - other.sum()
return loss
schedule = Schedule1F1B(stage, n_microbatches=4, loss_fn=loss_fn)
if rank == 0:
inputs = {
'input_ids': torch.zeros((4, 512), dtype=torch.long).to(device),
'attention_mask': torch.ones((4, 512), dtype=torch.bool).to(device),
}
schedule.step(
**inputs,
)
elif rank == world_size - 1:
losses = []
output = schedule.step(target=torch.randn(4, 512).to(device), losses=losses)
print(f"losses: {losses}")
else:
schedule.step()(pt) fyguan@beast:~/disk20$ torchrun --nproc-per-node 2 pipelining_model_backward.py
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851]
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851] *****************************************
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0519 11:42:34.313000 53989 site-packages/torch/distributed/run.py:851] *****************************************
[Rank 1] Starting model init on cuda:1
[Rank 0] Starting model init on cuda:0
Loading weights: 100%|████████████████████████████████████████████████████████████████████████████████████████████| 272/272 [00:00<00:00, 41777.16it/s]
Loading weights: 100%|████████████████████████████████████████████████████████████████████████████████████████████| 272/272 [00:00<00:00, 38255.34it/s]
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(49152, 576)
(layers): ModuleList(
(0-29): 30 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=576, out_features=576, bias=False)
(k_proj): Linear(in_features=576, out_features=192, bias=False)
(v_proj): Linear(in_features=576, out_features=192, bias=False)
(o_proj): Linear(in_features=576, out_features=576, bias=False)
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=576, out_features=1536, bias=False)
(up_proj): Linear(in_features=576, out_features=1536, bias=False)
(down_proj): Linear(in_features=1536, out_features=576, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm((576,), eps=1e-05)
(post_attention_layernorm): LlamaRMSNorm((576,), eps=1e-05)
)
)
(norm): LlamaRMSNorm((576,), eps=1e-05)
(rotary_emb): LlamaRotaryEmbedding()
)
(lm_head): Linear(in_features=576, out_features=49152, bias=False)
)
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(49152, 576)
(layers): ModuleList(
(0-29): 30 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=576, out_features=576, bias=False)
(k_proj): Linear(in_features=576, out_features=192, bias=False)
(v_proj): Linear(in_features=576, out_features=192, bias=False)
(o_proj): Linear(in_features=576, out_features=576, bias=False)
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=576, out_features=1536, bias=False)
(up_proj): Linear(in_features=576, out_features=1536, bias=False)
(down_proj): Linear(in_features=1536, out_features=576, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm((576,), eps=1e-05)
(post_attention_layernorm): LlamaRMSNorm((576,), eps=1e-05)
)
)
(norm): LlamaRMSNorm((576,), eps=1e-05)
(rotary_emb): LlamaRotaryEmbedding()
)
(lm_head): Linear(in_features=576, out_features=49152, bias=False)
)
/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/copyreg.py:99: FutureWarning: `isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
return cls.__new__(cls, *args)
/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/copyreg.py:99: FutureWarning: `isinstance(treespec, LeafSpec)` is deprecated, use `isinstance(treespec, TreeSpec) and treespec.is_leaf()` instead.
return cls.__new__(cls, *args)
[rank0]: Traceback (most recent call last):
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 328, in placeholder
[rank0]: return next(self.args_iter)
[rank0]: ^^^^^^^^^^^^^^^^^^^^
[rank0]: StopIteration
[rank0]: The above exception was the direct cause of the following exception:
[rank0]: Traceback (most recent call last):
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/stage.py", line 892, in forward_one_chunk
[rank0]: output = self.forward_maybe_with_nosync(*composite_args, **composite_kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/stage.py", line 762, in forward_maybe_with_nosync
[rank0]: out_val = self.submod(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/graph_module.py", line 949, in call_wrapped
[rank0]: return self._wrapped_call(self, *args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/graph_module.py", line 461, in __call__
[rank0]: raise e
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/graph_module.py", line 447, in __call__
[rank0]: return super(self.cls, obj).__call__(*args, **kwargs) # type: ignore[misc]
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl
[rank0]: return forward_call(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "<eval_with_key>.474", line 6, in forward
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl
[rank0]: return forward_call(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/export/unflatten.py", line 216, in forward
[rank0]: return torch.fx.Interpreter(self, graph=self.graph).run(
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 200, in run
[rank0]: self.env[node] = self.run_node(node)
[rank0]: ^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 297, in run_node
[rank0]: return getattr(self, n.op)(n.target, args, kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 431, in call_module
[rank0]: return submod(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl
[rank0]: return forward_call(*args, **kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/export/unflatten.py", line 216, in forward
[rank0]: return torch.fx.Interpreter(self, graph=self.graph).run(
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 200, in run
[rank0]: self.env[node] = self.run_node(node)
[rank0]: ^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 297, in run_node
[rank0]: return getattr(self, n.op)(n.target, args, kwargs)
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/fx/interpreter.py", line 333, in placeholder
[rank0]: raise RuntimeError(
[rank0]: RuntimeError: Expected positional argument for parameter unsqueeze_default, but one was not passed in!
[rank0]: While executing %unsqueeze_default : [num_users=1] = placeholder[target=unsqueeze_default]
[rank0]: Original traceback:
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/transformers/models/llama/modeling_llama.py", line 474, in forward
[rank0]: outputs: BaseModelOutputWithPast = self.model(
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/transformers/models/llama/modeling_llama.py", line 397, in forward
[rank0]: position_ids = position_ids.unsqueeze(0)
[rank0]: Use tlparse to see full graph. (https://github.com/pytorch/tlparse?tab=readme-ov-file#tlparse-parse-structured-pt2-logs)
[rank0]: While executing %rotary_emb : [num_users=1] = call_module[target=rotary_emb](args = (), kwargs = {})
[rank0]: Original traceback:
[rank0]: None
[rank0]: Use tlparse to see full graph. (https://github.com/pytorch/tlparse?tab=readme-ov-file#tlparse-parse-structured-pt2-logs)
[rank0]: The above exception was the direct cause of the following exception:
[rank0]: Traceback (most recent call last):
[rank0]: File "/mnt/disk20/user/fyguan/pipelining_model_backward.py", line 79, in <module>
[rank0]: schedule.step(
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/schedules.py", line 604, in step
[rank0]: self._step_microbatches(
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/schedules.py", line 873, in _step_microbatches
[rank0]: output = self._stage.forward_one_chunk(
[rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank0]: File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/pipelining/stage.py", line 900, in forward_one_chunk
[rank0]: raise RuntimeError(exc_msg) from e
[rank0]: RuntimeError:
[rank0]: [Stage 0] failed to run forward:
[rank0]: args: ()
[rank0]: kwargs: {'input_ids': 'Tensor(torch.Size([1, 512]), grad=False, dtype=torch.int64)', 'attention_mask': 'Tensor(torch.Size([1, 512]), grad=False, dtype=torch.bool)'}
[rank0]:
[rank0]:[W519 11:42:51.791357236 ProcessGroupNCCL.cpp:1575] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator())
W0519 11:42:54.151000 53989 site-packages/torch/distributed/elastic/multiprocessing/api.py:1012] Sending process 54075 closing signal SIGTERM
E0519 11:42:54.469000 53989 site-packages/torch/distributed/elastic/multiprocessing/api.py:986] failed (exitcode: 1) local_rank: 0 (pid: 54074) of binary: /mnt/disk20/user/fyguan/miniconda3/envs/pt/bin/python3.12
Traceback (most recent call last):
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/bin/torchrun", line 6, in <module>
sys.exit(main())
^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 362, in wrapper
return f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/run.py", line 990, in main
run(args)
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/run.py", line 981, in run
elastic_launch(
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 170, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/disk20/user/fyguan/miniconda3/envs/pt/lib/python3.12/site-packages/torch/distributed/launcher/api.py", line 317, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
pipelining_model_backward.py FAILED
------------------------------------------------------------
Failures:
[1]:
time : 2026-05-19_11:42:54
host : beast
rank : 1 (local_rank: 1)
exitcode : -15 (pid: 54075)
error_file: <N/A>
traceback : Signal 15 (SIGTERM) received by PID 54075
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
time : 2026-05-19_11:42:54
host : beast
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 54074)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
============================================================Collecting environment information...
PyTorch version: 2.11.0+cu130
Is debug build: False
CUDA used to build PyTorch: 13.0
ROCM used to build PyTorch: N/A
OS: Ubuntu 24.04.4 LTS (x86_64)
GCC version: (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version: Could not collect
CMake version: version 3.28.3
Libc version: glibc-2.39
Python version: 3.12.13 | packaged by conda-forge | (main, Mar 5 2026, 16:50:00) [GCC 14.3.0] (64-bit runtime)
Python platform: Linux-6.18.20-fyguan-x86_64-with-glibc2.39
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to:
GPU models and configuration:
GPU 0: NVIDIA H200 NVL
GPU 1: NVIDIA H200 NVL
GPU 2: NVIDIA H200 NVL
GPU 3: NVIDIA H200 NVL
Nvidia driver version: 590.48.01
cuDNN version: Could not collect
Is XPU available: False
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
Caching allocator config: N/A
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 52 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 256
On-line CPU(s) list: 0-255
Vendor ID: AuthenticAMD
Model name: AMD EPYC 9555 64-Core Processor
CPU family: 26
Model: 2
Thread(s) per core: 2
Core(s) per socket: 64
Socket(s): 2
Stepping: 1
Frequency boost: enabled
CPU(s) scaling MHz: 84%
CPU max MHz: 4410.8110
CPU min MHz: 1210.8110
BogoMIPS: 6391.45
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpuid_fault cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 invpcid cqm rdt_a avx512f avx512dq adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx_vnni avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect movdiri movdir64b overflow_recov succor smca avx512_vp2intersect flush_l1d debug_swap amd_lbr_pmc_freeze
Virtualization: AMD-V
L1d cache: 6 MiB (128 instances)
L1i cache: 4 MiB (128 instances)
L2 cache: 128 MiB (128 instances)
L3 cache: 512 MiB (16 instances)
NUMA node(s): 2
NUMA node0 CPU(s): 0-63,128-191
NUMA node1 CPU(s): 64-127,192-255
Vulnerability Gather data sampling: Not affected
Vulnerability Ghostwrite: Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Old microcode: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Mitigation; Reduced Speculation
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; STIBP always-on; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsa: Not affected
Vulnerability Tsx async abort: Not affected
Vulnerability Vmscape: Mitigation; IBPB before exit to userspace
Versions of relevant libraries:
[pip3] numpy==2.4.3
[pip3] nvidia-cublas==13.1.0.3
[pip3] nvidia-cuda-cupti==13.0.85
[pip3] nvidia-cuda-nvrtc==13.0.88
[pip3] nvidia-cuda-runtime==13.0.96
[pip3] nvidia-cudnn-cu13==9.19.0.56
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-curand==10.4.0.35
[pip3] nvidia-cusolver==12.0.4.66
[pip3] nvidia-cusparse==12.6.3.3
[pip3] nvidia-cusparselt-cu13==0.8.0
[pip3] nvidia-nccl-cu13==2.28.9
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvtx==13.0.85
[pip3] torch==2.11.0+cu130
[pip3] torchaudio==2.11.0+cu130
[pip3] torchvision==0.26.0+cu130
[pip3] triton==3.6.0
[conda] cuda-nvrtc 13.2.51 hecca717_0 conda-forge
[conda] libcufft 12.2.0.37 hecca717_0 conda-forge
[conda] numpy 2.3.5 pypi_0 pypi
[conda] nvidia-cublas 13.1.0.3 pypi_0 pypi
[conda] nvidia-cuda-cupti 13.0.85 pypi_0 pypi
[conda] nvidia-cuda-nvrtc 13.0.88 pypi_0 pypi
[conda] nvidia-cuda-runtime 13.0.96 pypi_0 pypi
[conda] nvidia-cudnn-cu13 9.19.0.56 pypi_0 pypi
[conda] nvidia-cufft 12.0.0.61 pypi_0 pypi
[conda] nvidia-curand 10.4.0.35 pypi_0 pypi
[conda] nvidia-cusolver 12.0.4.66 pypi_0 pypi
[conda] nvidia-cusparse 12.6.3.3 pypi_0 pypi
[conda] nvidia-cusparselt-cu13 0.8.0 pypi_0 pypi
[conda] nvidia-nccl-cu13 2.28.9 pypi_0 pypi
[conda] nvidia-nvjitlink 13.0.88 pypi_0 pypi
[conda] nvidia-nvtx 13.0.85 pypi_0 pypi
[conda] torch 2.11.0+cu130 pypi_0 pypi
[conda] torchaudio 2.11.0+cu130 pypi_0 pypi
[conda] torchvision 0.26.0+cu130 pypi_0 pypi
[conda] triton 3.6.0 pypi_0 pypicc @awgu @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @pragupta @msaroufim @dcci @aditvenk @weifengpy
Vote matrix · Quick signals
Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Still need to ship something?
×6Another batch ranked right after the header list — different links, same matching logic.
TRENDING
- Feature Request: Configurable per-minute rate limiting (RPM) for models to prevent 429 errors
- Android: Hermes App + Termux install share ~/.hermes and cause silent permission loops
- hermes update emits unicode-animations ANSI demo in non-interactive logs
- hermes update downgrades aiohttp from 3.13.4 to 3.13.3
- npm install warns about deprecated @babel/plugin-proposal-private-methods
- DingTalk inbound media URLs are skipped as unreadable native image paths
- fix(dashboard): ChatPage clears header action buttons on ALL pages, not just Sessions
- [Bug]: check_web_api_key() hardcodes built-in backends — third-party web search plugins silently disabled
- Hermes Web UI 修复经验：GatewayManager 补丁、进程 D 状态、数据库升级问题
- Telegram gateway can silently drop turn after /stop with response=0 chars while internal work continues
- Bug Report: v0.14.0 上下文污染 — 历史回复碎片回注到新请求
- Bug: hermes skills search table truncates Identifier column — install fails with copied value
- [skills-index-watchdog] Skills index is stale or degraded (degraded)
- Discord approval embed not rendering on web/mobile — embed data present in API but invisible
- Idea: Discord voice-channel participation / opt-in auto-join mode
- [Feature]: Claude Code--ultrawork
- build-arm64 job deterministically fails on cold cache (Azure SAS token expires mid-build)
- [Enhancement] computer_use: action=type should fall back to key events for terminal emulators (Ghostty/Terminal.app/iTerm2)
- Feature Request: Session Recovery on Temporary Provider Outage
- [Bug]: Hermes dashboard not working on NixOS (container)
- [Feature]: Add option to ignore @all/@everyone mentions in Feishu group chats
- QQ Bot WebSocket 频繁断开：长时间工具执行阻塞 asyncio 事件循环导致心跳超时
- patch tool: new_string escape sequences (\t) get written literally
- Feature Request: i18n / 多语言支持（国际化）
- Bug: web_crawl schema lets models auto-guess "instructions" instead of asking the user via clarify
- feat: `!command` prefix for direct shell execution (like Claude Code)
- Expose currently-running cron jobs via /api/jobs (or new endpoint)
- [Bug]: Kanban parent-child handoff: scratch workspace GC destroys artifacts before child can read them
- [Bug, Windows] hermes gateway restart loses session context — planned_stop_marker not written before SIGTERM
- [Bug]: Codex→DeepSeek fallback sends assistant turns without reasoning_content → HTTP 400 (require-side cross-provider failover)
- [Bug]: Update got stuck half way, reboot it, then ModuleNotFoundError: No module named 'hermes_cli'
- Kanban dispatcher corrupt-board handling and multi-profile gateway ownership ambiguity
- Gateway can resend a short fallback message when the real final Telegram response was already delivered
- [BUG] Bedrock: Fix 'Invalid API Key format' for presigned URL tokens
- Secret redaction corrupts code syntax in tool output (write_file, execute_code, terminal)
- Unable to connect Ollama Cloud with Pro Subscription to Hermes
- feat: fuzzy substring matching for /skill autocomplete
- PRD: Autonomous market-impact prediction briefing system
- Kanban dashboard should support task/card deep links
- [Feature] Native Feishu CardKit Streaming: consolidate best-in-class implementations
- [Feature]: Inject mental model into context when using Hindsight
- Interactive CLI hides tool output despite display.tool_progress=all, and hermes chat -v does not restore it
- fix(api_server): _handle_responses drops text.format JSON schema — structured output constraints silently ignored
- state.db FTS corruption goes undetected — no integrity check, no repair path
- bug: fallback routing can select text-only models for image requests and hide the primary failure
- feat(kanban): persist worker session_id per run and pass --resume on respawn after unblock
- feat(kanban): support GitHub/OMO lifecycle bridge for Xiyou-style automation
- Expose update-safe TUI/composer hooks for voice transcript and composer events
- Hide or configure voice transcript status rows in editable dictation mode
- [Feature]: Per-Tool / Per-Toolset Approval Policies
- Context compression creates orphan sessions missing from state.db
- messaging platform
- feat: Add read-only / silent monitoring mode for WhatsApp adapter
- double-.hermes path mismatch, the HOME env var leak, and the fallback-notification UX problem
- Bug: Plattform-Bundle name `hermes-yuanbao` in `agent.disabled_toolsets` silently kills ALL tools in gateway path (Telegram + cron), CLI unaffected
- CLI /yolo (in-chat) does not bypass dangerous command approvals — env var freeze + missing enable_session_yolo call
- OpenAI Codex provider crashes with "'NoneType' object is not iterable" (HTTP None)
- DEEPSEEK_API_KEY blocked by env blocklist in gateway process — cron jobs fail with deepseek provider
- fix(feishu): Card action callback routing issues - invalid message_id and unrecognized /card command
- Discord plugin: profiles without explicit `discord:` block silently get `require_mention=true` + `auto_thread=true` (regression in cc8e5ec2a)
- [Bug]: DISCORD_ALLOWED_ROLES ignored by gateway _is_user_authorized — role-authorized users get 'Unauthorized user' rejection
- [Bug]: /new, /clear, and /reset commands freeze the terminal session
- openai-codex subscription backend returns HTTP 200 with response.output=None, causing Slack/cron failures
- RFC: Centralized Model/Provider Registry
- bug: openai-codex provider — TypeError: 'NoneType' object is not iterable on every request (gpt-5.5)
- [Feature]: Source-aware instruction gate — architectural mitigation for indirect prompt injection
- Named custom provider stale_timeout_seconds ignored because runtime provider is normalized to `custom`
- guard test (ignore)
- [Feature]: per-platform LLM request_overrides (extra_body / reasoning_effort / service_tier)
- One-shot smoke: add Flue-backed orchestration fixture
- Gateway should not treat stale Codex app-server progress as final response after post-tool silence
- `docker_run_as_host_user: true` breaks bundled skills: Hermes home is mounted into `/root/.hermes` but the container runs as a non-root user (`HOME=/home/pn`)
- [Bug]: gateway api_server streaming bypasses server-side tool-call loop when chat_template_kwargs.enable_thinking=false (model emits tool name as plain text)
- [Feature]: Pre-install python-telegram-bot in Umbrel Hermes Docker image
- YouTube Shorts filter not working in youtube-content skill
- v0.15.0 PyPI release breaks ALL platforms — plugin.yaml manifests missing from package
- RFC: On-demand tool/skill/MCP discovery — decouple schema registration from process lifecycle
- Pixshelf: local-first stock photo workflow command center
- [Bug]: baoyu infographic skill should not silently bypass image_generate
- Pixshelf v1.5: manual submission tracking for stock agencies
- `hermes config set` silently accepts unknown keys, writing them where the runtime never reads
- Honcho memory prefetch hang on fresh CLI subprocess in v0.15.0 (regression from #27190)
- [Bug] v0.15.0 Docker image: stage2-hook.sh, main-wrapper.sh missing; container_boot module removed
- Feature: Reduce cache-read token overhead for DeepSeek providers — configurable cache_ttl, skills snapshot trimming, memory compaction
- Windows: three bugs from daily use (plugin discovery, gateway exit code, Unicode decode
- holographic memory: HRR silently degrades to FTS5 when numpy is missing
- Make max_tokens configurable for aux vision calls
- Conversation compression desynchronizes session ID between agent context and gateway routing, causing silent message loss
- [Bug]: v0.15.0 Docker image:The TUI cannot be used in the dashboard.
- cron: skip_memory=True blocks fact_store/memory tools from all cron jobs
- TUI: Node.js OOM crash when agent uses browser tools repeatedly
- feat: model_profiles — per-model toolset and memory config
- Automatic background skill patching disrupts active sessions (severe impact on local models)
- ensure_hermes_home() creates root-owned dirs in profile subdirectories when kanban workers are dispatched
- Feature: opt-in webhook bypass for DISCORD_ALLOW_BOTS — allow operator-initiated probes without weakening bot-loop guard
- v0.15.0: Codex requests fail HTTP 400 when participant display_name contains non-ASCII (emoji breaks input[].name pattern)
- Architecture: State Persistence Precedence (Memory vs Skills vs Hooks)
- [Bug]: cronjob tool: create action always fails with "schedule is required for create" even when parameters are provided
- codex-oauth: 'NoneType' object is not iterable in _run_codex_stream (gpt-5.5) — every turn fails non-retryably
- Docs/Config: Plugin local scope enablement ambiguity
- [Bug]: CLI freezes after using /new command (WSL)
- Profile Codex auth can ignore global credential pool when local state is stale
- [workflow-engine] CRITICAL: variable substitution crashes on regex metachars in user input
- [workflow-engine] HIGH: loop and bash nodes leak subprocesses on timeout
- [workflow-engine] HIGH: README documents config env vars the engine never reads
- [workflow-engine] MEDIUM: workflow_run rate limit bypassable via concurrent calls (TOCTOU)
- [workflow-engine] chore: manifest gaps, side-effectful register(), dead code, unauth kanban dispatch
- [mcp_lazy] HIGH: synthetic mcp_server_<name> stub collides with a real MCP server named 'server'
- [mcp_lazy] HIGH: promote_server eager flag documented but never persisted
- [mcp_lazy] MEDIUM: _prev_mode dict leaks and goes stale; not cleared on session evict
- [mcp_lazy] MEDIUM: get_pool has unlocked check-then-set race on pool creation
- [mcp_lazy] MEDIUM: pre_tool_call gives no guidance for unpromoted server-stub calls
- [mcp_lazy] chore: undeclared pre_tool_call hook, nonexistent 'mcp_load_tools' name in docs, missing tests
- [a2a_fleet] CRITICAL: server never auto-starts — register() runs outside an event loop
- [a2a_fleet] CRITICAL: auth_required defaults to false on a cross-machine surface
- [a2a_fleet] HIGH: remove invented disable() hook — loader never calls it, port leaks on reload
- [a2a_fleet] HIGH: plugin.yaml missing kind / provides_tools / requires_env (token env undeclared)
- [a2a_fleet] MEDIUM: tighten wide-open CORS, anonymous /health peer leak, and peer-URL SSRF
- [a2a_fleet] MEDIUM: relocate tests to tests/plugins/ and cover sync-register + auth-default paths
- xai-oauth auxiliary client incorrectly uses Responses API (CodexAuxiliaryClient), causing 403 on compression/vision/web_extract
- [Bug]: Direct Copilot gpt-5.5 large resumes are killed by 12s Codex TTFB watchdog
- [Bug]: `hermes uninstall` does not work on Windows
- TUI: Thinking block leaks raw JSON and Σ character
- Hostinger VPS: migration Hermes Agent → Hermes WebUI impossible (tini + UID mismatch + sessions)
- /goal judge over-continues exploratory goals unless the assistant explicitly says the goal is complete
- /goal auto-continuation can be amplified by preflight compression/session split and resurrect stale task state
- Dashboard infinite reload loop in loopback mode — GET /api/auth/me returns 401 on every page load
- [Bug]: Provider/LLM switch leaves stale encrypted_content causing 400 errors on Telegram sessions
- [Bug]: Infinite reload loop / React state loop on Sessions tab (Firefox + Chrome) — repeated 401 on /api/auth/me (v0.15.0)
- show_reasoning should work independently of streaming in CLI mode
- Feature Request: Strip reasoning/<think> blocks from TTS preprocessing
- mcp add / mcp test raise NameError when mcp package not installed
- v0.14.0 dashboard breaks behind reverse proxies — two regressions
- Skills hub creates empty category directories when no skills installed
- [Bug]: Custom endpoint: ChatCompletions returns content, but Hermes treats response as empty (v0.14.0)
- fix: atomic_replace() fails with EXDEV when HERMES_HOME is a cross-filesystem symlink
- fix(gateway): Feishu session cancellation orphans session guard, permanently blocking messages
- Custom endpoint pricing can overestimate Crof qwen3.5-9b cost by 1,000,000x
- MCP OAuth callback: module-level port global causes port collisions and structural weaknesses vs upstream
- Bug: send_message tool bypasses validate_media_delivery_path security check
- Proposal: Add Mnemosyne to official memory provider documentation
- feat(swarm): support custom verifier/synthesizer body + skills
- Template conversion failed
- Error occurred in the operation of the agent node in the workflow.
- PubSub client overrides Sentinel client when REDIS_USE_SENTINEL is enabled
- Frontend description of the Retrieval node output does not match the actual output
- JSON type input var raise Intenal server error
- cannot extract elements from a scalar
- 负载均衡 为模型配置多组凭据，并自动调用，此功能无法选择
- add models is error
- panic: could not create filter
- Persist partially generated messages when /chat-messages/:task_id/stop is called
- MCP server connection fails with 403 — request never leaves Dify (SSRF proxy suspected)
- Support durable async execution backends for long-running workflow steps
- [Xiaomi MiMo] Credentials validation fails with 400 "Not supported model mimo-v2-flash" when using Token Plan endpoint (v0.0.7)
- After clicking preview on a parent-child segmented knowledge base, it shows 0 chunks
- Retrieval score differs between UI upload (.docx) and API upload (.txt) despite identical chunk content and embedding model
- gemini cli crash again
- Xbox gift card code damage
- Damage caused by the gemini cli crash
- ioctl(2) failed, EBADF (Bad File Descriptor)
- Feat: Support Bun as an alternative runtime/package manager for updates and extensions
- fatal error again!!!!
- ioctl error
- Critical Crash: ioctl(2) failed, EBADF in ShellExecutionService.resizePty
- ioctl(2) failed, EBADF
- v0.44.0 Regression: Critical crash with ioctl(2) failed, EBADF during PTY resize
- Crash on startup: ioctl(2) failed, EBADF in UnixTerminal.resize
- Crash: `ioctl(2) failed, EBADF` in `node-pty` during PTY resize on macOS
- Gemini CLI crashes with `ioctl(2) failed, EBADF` in `node-pty` during `resizePty`
- Remote Role
- ERROR ioctl(2) failed, EBADF /home/mich
- RangeError: Maximum call stack size exceeded
- EBADF Error during folder creationg broke session and terminal glitches
- MAIP / Gargoub Project - Mediterania - North Coast
- Gemini cli crash again in this morning
- ERROR ioctl(2) failed, EBADF
- Verified node install fails — Checksum verification failed (Cloud)
- The extended debugging key did not arrive during registration.
- CollaborationPane unmounts collaboration store on single-user instances, causing permanent "No network connection" state
- Workflow cannot be saved when the name contains "->" (Potentially malicious string)
- automation does not work and does not show an error
- Raj Ai Automation
- Default Data Loader: DOMMatrix is not defined error
- Feature: Per-node execution timestamp overlay on canvas during workflow run
- AI Agent + Vertex `gemini-3.5-flash`: 400 "missing thought_signature" on sequential multi-turn tool calls (post-#24982)
- PDF Loader in Pinecone Vector Store fails due to pdf-parse version conflict (v2 not supported)
- emailReadImap: add UID deduplication, batch size cap, and numeric uid enforcement
- Manual node execution fails with "Could not find a node" when autosave is disabled (N8N_WORKFLOWS_AUTOSAVE_DISABLED)
- Schedule Trigger stopped firing — workflow Published & active, manual executions succeed, no automated fires for 2+ hours
- [MCP SDK] create_workflow_from_code intermittently returns HTTP 500, often as a false negative (workflow persists anyway, causing duplicates on retry)
- Credential-load wedge: workflows using googleApi/jwtAuth credentials silently fail to execute after key rotation
- Google Sheets Trigger every minute is not working manual Execute is working sent email
- [BUG] Plugin marketplace MCP connector remains stuck "still connecting" when mcp-remote requires OAuth
- [redacted at user request]
- Opus 4.7 behavioral regression: loaded instruction-following discipline degraded in recent Claude Code/Cowork updates
- [BUG] Tailscale via Homebrew CLI + Mac App Store GUI, both Macs on macOS, Cowork blocked by VPN detector despite Tailscale being a mesh VPN with no traffic interception
- stopShellPty on tab switch kills active sessions (exit 143) — regression in May 27 build
- [BUG] Long URLs are broken into multiple lines and become unclickable in terminal output
- [BUG] claude rm/stop/reap SIGKILLs background session tree without SIGTERM grace, orphaning git index.lock and similar
- [BUG] Default git workflow in the system prompt was pushed without context or consent
- [MODEL] Inconsistent output quality / Ignoring instructions (overfitting and inappropriate repetition of Korean vocabulary)
- You've hit your weekly limit · resets May 31 at 5pm (Asia/Shanghai)
- Paid yearly subscription silently downgraded to Free with no user action
- [Regression v2.1.153] Plugin bash hooks fail with "echo: write error: Permission denied" on Windows (claude-mem, shell: "bash")
- [BUG] Connector toggles in conversation are not clickable — must click text label instead
- [remote-control] Input from mobile app/browser not reaching host session — output works fine
- Model fails to read/reference CLAUDE.md contents despite being loaded in context
- [BUG] Claude Desktop reinstall destroys Code chat history (transcripts + Recents) while regular Chat history, project files, and memory all survive
- Bypass mode clamps to Accept Edits even with the toggle ON (Claude Code Desktop 1.9255.2 / CC 2.1.149)
- [BUG] TUI input freezes randomly mid-typing — entire prompt becomes unresponsive for minutes
- [BUG] Cowork downloads Linux ELF binary instead of macOS binary on macOS Sonoma 14.8.7 — exit code 132 (SIGILL) on every session
- [Feature Request] Persistent project memory — sessions forget everything on close, forcing users to keep many sessions open
- [Bug] Thread context stale after sleep/resume, returns outdated date and calendar data
- [FEATURE] Add context window usage indicator and warning before auto-compaction
- [BUG] Dictation error: Invalid character in header content ["x-config-keyterms"] on Windows
- [Bug] Anthropic API Error: Server rate limiting despite normal usage
- Does delegating work to `claude -p` subprocesses reduce context accumulation in the parent session?
- [BUG] Claude Code hangs on M1 Mac when terminal says "opening browser to sign in" and browser opens
- [BUG] Claude_Preview MCP preview_start spawns dev server with main-repo cwd instead of session's worktree cwd
- [Bug] Anthropic API Error: Server rate limiting during request execution
- [Bug] Anthropic API Error: Server rate limiting on concurrent requests
- [Bug] Ultraplan ready notification fires before cloud agent completes execution
- [BUG] API 500 ERROR ALL THROUGHOUT THE DAY
- [BUG] Cowork: Live Artifacts folder path changed in 1.9255.2, no automatic migration from Documents\Claude\Artifacts
- [Bug] Auto-compact never triggers despite statusline reporting "100% context used" (v2.1.153, Max sub, 200K mode)
- [BUG] [Desktop / macOS] 'Open in → New Window' detached session: font renders smaller than main, no per-window controls, Cmd+/Cmd- keystrokes routed to main window instead
- Feature request: option to switch between classic and new minimal UI
- [Feature Request] Show timestamps for each message
- [BUG] Terminal corruption when permission prompt appears while navigating Agent Teams agent selection menu
- [FEATURE] Allow users to customize the background color of the Claude desktop app beyond the current light/dark theme presets.
- [BUG] Statusline not displaying on Windows [fixed]
- Background agent UI Stop button is a no-op for stuck agents — process keeps consuming tokens
- Background agents silently die on session pause/resume — no completion notification, no work recovery
- Add option to hide email address from welcome banner
- [BUG] SSH Remote: `projects` field in remote ~/.claude.json becomes null after desktop restart — jsonl files intact, UI shows 'No messages yet' for every session
- [Bug] Claude Code not applying fixes despite claiming to complete tasks
- billing is unfair and poorly documented
- [BUG] Claude Code on the web: declared plugins inactive on first session, require restart to fully load
- [BUG] Restore from archive deleted sessions instead of restoring them
- [BUG] M365 connector fails with AADSTS50011 in Cowork — localhost vs 127.0.0.1 redirect URI mismatch
- claude agents: workflow slash-commands missing from dispatch-input completion (regression-adjacent to #61424)
- Claude Desktop's Info.plist missing TCC usage strings, blocks all EventKit-based MCP servers
- False-positive safety blocks on self-administered governance amendments — request for owner-authority mode for verified professional users
- [BUG] Stop pushing "AUTO"-mode
- [DOCS] Plugin marketplace guide omits `skipLfs` option for git-based sources
- [DOCS] MCP docs omit combined startup notification for MCP server and connector authentication
- [DOCS] Agent view docs omit macOS Privacy & Security identity for background agents
- [DOCS] Npm update docs do not explain release-channel behavior for `claude update`
- [DOCS] Agent SDK docs omit `subagent_type: "claude"` worktree and output persistence behavior
- [DOCS] Background session docs omit `$CLAUDE_JOB_DIR` temp-file behavior
- [FR] mask env-var values in 'claude mcp get <server>' output
- [FR] subagent worktrees should not inherit stale local 'user.email' from prior dispatches
- [BUG] Windows: Grep tool leaks rg.exe + conhost.exe processes (~2000 zombies / 14 GB RAM in long sessions)
- [BUG] Stats dashboard "Peak hour" appears off by one hour
- [BUG] Diff highlight (teal SGR background) bleeds past changed text in 2.1.150–2.1.153
- [FEATURE] confirm before deleting session
- Plugin PostToolUse hooks still silently skip in Claude Desktop / Cowork (re-filing closed #51904)
- /code-review skill: silent fallback to main...HEAD reviews other people's commits, and JSON-only output is hard to read
- Monitor tool doesn't source the shell snapshot like Bash does; PATH-dependent tools (jq, sleep, etc.) fail in Monitor commands on macOS/Nix
- [Bug] Long input lines truncated with ellipsis while typing instead of wrapping in terminal UI
- [FEATURE] VS Code extension: Render submitted user messages as Markdown in chat
- OSC 52 copy from Claude TUI doesn't reach clipboard inside tmux (regression in 2.1.146–2.1.153)
- [BUG] RemoteTrigger create/update returns HTTP 400 with circular error: "event_type is required" / "unknown field event_type"
- [BUG] Option to hide or minimize the built-in "status footer" (multi-line debug/cost panel) [re-raise of #31475]
- [Bug] Feedback submissions being closed without review or action
- [FEATURE] Word-jump cursor navigation in Chat input (option+arrow / bindable actions)
- [FEATURE] ! shell mode: filesystem tab completion
- [BUG] API Error: Usage credits required for 1M context
- claude agents: OSC 52 clipboard emission broken in tmux (regression in 2.1.146–2.1.153)
- CLI crashes on macOS 15 M3 - exit code 1
- [FEATURE] Support Cmd+V image paste from clipboard
- [FEATURE] Enhance claude.ai M365 connector to support MS Planner
- [BUG] Slash command autocomplete hijacks pasted absolute file paths starting with /
- PreToolUse hook `if` filter false-positives on complex Bash commands
- [BUG] Diff panel hangs/whites out
- Feature Request: Support drag-and-drop for binary documents (.wps, .doc, .docx, .xlsx, .pdf) in VS Code extension
- [BUG] activation of 1M context in VSCode
- [FEATURE] Support i18n / language localization for built-in slash command outputs
- Ctrl+V para colar imagens deixou de funcionar no CLI (Windows, PowerShell)
- [FEATURE] Please add Norwegian (Bokmål/Nynorsk) language support to the Claude Code interface
- [BUG] OTel log events (claude_code.user_prompt, api_request_body, tool_decision, hook_execution_complete) emitted with empty trace_id/span_id while sibling spans correlate correctly
- [BUG] Cowork crashes on every message, no VM logs generated, missing AppData\Roaming\Claude
- [FEATURE] first-class session handoff + per-session token budgets for unattended runs
- [FEATURE] Smart paste: convert clipboard code to file reference chips (like Cursor)
- [Feature Request] Restore chat pin functionality to title chat submenu
- [BUG] SIGILL issues with version 2.1.153
- [BUG] Cowork plugin upload fails with generic "Plugin validation failed" when a `description` field in any SKILL.md frontmatter contains angle brackets (`<…>`)
- [BUG] Desktop App 2.1.144+: startup scanner deletes cliSessionId from claude-code-sessions local files on every launch — session not found on disk
- [Feature Request] Add keyboard shortcut to copy last message with proper formatting
- [MODEL] Opus 4.7 not 1M
- Allow naming/renaming background agents in `claude agents` view
- Stale worktrees in .claude/worktrees/ are never cleaned up, consuming massive disk space
- Agent worktrees are never cleaned up, silently consuming disk space
- Subagent worktrees not auto-cleaned when reviewer writes scratch files
- [Bug] Skill initialization hangs for extended duration in Plan Mode
- Claude Desktop writes malformed registry Run entry (nested escaped quotes) - crashes Windows Task Manager and other Run-key parsers
- IME candidate window shows at bottom-right corner instead of caret position (Windows CMD)
- [BUG] Pressing 'Escape' doesn't close the /BTW conversation when the main conversation is asking for approval
- [BUG] Opus 4.7 (1M) intermittently emits empty-string values for tool_use.input fields, killing the session
- FleetView agent UI shows "running" with incrementing elapsed time after agent has returned
- /doctor flags context-scoped cmd+c binding as macOS conflict (false positive)
- [BUG] Text Rendering in Elvish
- Desktop app: Bypass Permissions mode flips to Accept Edits on first prompt (M5 / macOS 26.5)
- [Workaround] Date-Weekday Verification Hook — Prevents Claude from writing wrong weekdays
- [BUG] Claude Code create c:/memfs directory without asking me.
- [BUG] Claude Code's Bash execution waits forever with no processes running
- [BUG] usage stays stuck waiting for 5 hr limit after upgrading to premium seat in team plan
- [Workflow tool] resume cache is unreachable for nontrivial workflows because LLM dispatchers can't transcribe args byte-exactly
- Code review (Preview): "Add a repository" shows no results for private GitHub org repos
- [BUG] /context commands blows up context
- [Feature Request] Add precache expiry hook to enable proactive compaction before token eviction
- [BUG] Context indicator shows 0% at session start despite ~20K+ tokens already loaded
- [Feature Request] Add semantic search for --resume session history
- [Feature Request] Add session search, tagging, and filtering capabilities
- [BUG] Cowork Dispatch reports "desktop not available" on Windows 11 while standard Cowork works normally
- [Bug] Claude Code provides incorrect suggestions with high confidence despite errors
- defaultMode: acceptEdits silently overrides per-path permissions.ask rules for Write/Edit
- [FEATUR configurable tip interval (e.g. tipIntervalSeconds: 30 in settings)E]
- Plugin marketplace fails to load: schema rejects 'displayName' key (v2.1.153)
- claude agents: in-session copy uses broken OSC 52 path while overview correctly uses tmux buffer
- [BUG] Plugin agent descriptions (and custom agents) load unconditionally into context — no parity with disable-model-invocation for skills
- Crashed ultrareview consumed a free credit despite producing zero findings
- [Bug] Character rendering issue - invisible or missing text display
- [BUG] Cowork: processo Claude Code encerra com código 3 — .claude.json não contém token de autenticação (Windows 11 25H2)
- [BUG] 2.1.153 silently discards tools/list response from rmcp 0.12.0 HTTP MCP server (works in 2.1.152, wire-identical handshake)
- VS Code extension: option to auto-resume last session when reopening a workspace folder
- [Bug] Conversation continuation failure
- [BUG] Cowork crashes every time I start a new chat or attempt to continue an existing one in any project. The error displayed is: "Claude Code è andato in crash
- [Bug] Unannounced quota changes
- Native update/install fails with 'socket connection was closed unexpectedly' behind proxy — undici TLS incompatibility
- [BUG] Session name reverting after manual change
- [BUG] 非正常思考，上下文过长时，一直显示思考，点击interrupt按钮失效
- Honor `tools:` frontmatter when an agent is invoked via `@mention` — strip `Task` only when the agent did not declare it
- macOS TCC popup still recurring on v2.1.153 — "2.1.153" would like to access data from other apps
- Claude Code leaks pty handles — exhausts pseudo-terminals on macOS after long session
- [Bug] Agent fails to execute or respond to user input
- [BUG] Persistent "Expecting value: line 1 column 1 (char 0)" JSON parse error after tool execution
- [Feature Request] Implement proactive unit test coverage recommendations for recurring bugs
- VS Code panel lacks status line + terminal lacks image paste in Codespaces, forcing a tradeoff
- `/powerup` only shows ~10 lessons — allow viewing the full catalog
- [Bug] Context contamination after auto-compact with unrelated email draft of Tejo/Sado Basin
- [Bug] VSCode terminal output displays corrupted text with garbled symbols
- [Feature Request] Add LaTeX/KaTeX math rendering to TUI
- [Bug] Sub-agent PR review results not validated by orchestrating agent
- Subagents on Pro 1M tier: trivial probes pass, real workloads fail at first tool call (probe-vs-workload divergence)
- Path-scoped rules and subdirectory CLAUDE.md not loaded when creating new files matching the pattern
- AskUserQuestion: cancelling during extended thinking poisons the whole session with 400 'thinking blocks cannot be modified' (2.1.153); concurrent prompts overwrite each other
- Ideas Missing from Claude Cowork Menu (Windows)
- [BUG_BOUNTY_SAFE_POC_2026] Prompt Injection RCE Test - Command Execution Proof
- [BUG] Cowork scheduled task: execution history row not showing after successful run
- Resuming an extended-thinking session fails permanently with 400 "thinking blocks cannot be modified" (transcript stores thinking text as empty but keeps signature)
- [Bug] Plugin-registered CwdChanged and FileChanged hooks don't fire (settings.json works) — v2.1.153
- Auto-archive on PR merge / branch delete — clarify autoArchiveSessions semantics or add dedicated opt-out
- `claude mcp add` echoes Authorization header value verbatim to stdout, leaks bearer tokens to terminal and session transcripts
- [BUG] Bug report — /insights skill, Claude Code The /insights skill outputs a malformed file path.
- Plugin slash commands render with '*'-inline format instead of two-column, despite matching official plugin shape
- [Bug] Unexpected long text generation without user input or goal
- [Bug] Thinking blocks causing task progression blocked without user modification
- [BUG] (Critical!) contamination by an unknown session simirlar to the report => [Bug] Context contamination after auto-compact with unrelated email draft of Tejo/Sado Basin #63137
- [Critical] Opus 4.7 Korean output degeneration — Korean grammar itself collapses in long contexts
- [BUG] Title: Autocompact buffer persists across /clear — wastes tokens for irrelevant old context
- [Bug] Auto-Compact loses user input before processing in conversation history
- Feature: per-invocation effort parameter + runtime session-config introspection for skills
- Auto-mode classifier mislabels Azure DevOps vote -5 as "Reject" when denying PR vote actions
- [BUG] Claude Desktop and Claude Code CLI never re-register MCP tools after OAuth 2.1 handshake on a remote HTTP server
- [BUG] Workspace file tags leak across sessions
- [BUG] Ink renderer crashes on Windows 11 build 26200 (Canary) duplicate banners, terminal mode leaks, mid-operation aborts
- [BUG] Claude Code Desktop issue
- PTY master fd leak in Claude desktop app exhausts macOS kern.tty.ptmx_max after ~2-3 days
- [BUG] Claude Code — Session Management after Unexpected Interruption
- [Windows] Cowork OpenTelemetry exporter does not initialize - zero events emitted to any destination, including loopback
- [Bug] Opus 4.7: 400 `thinking blocks ... cannot be modified` on long extended-thinking sessions, triggered by history-altering events (scheduled prompts / parallel tool-call cancellation)
- [BUG] API Error: Server is temporarily limiting requests (not your usage limit) · Rate limited
- Multi-plugin custom marketplace: only first plugin registered in installed_plugins.json, skills don't load
- [BUG] Git push through the SDK's git proxy fan-outs into ~500 GitHub REST API calls, exhausting the 5,000/hour budget after a handful of pushes
- [BUG] Claude took liberties it really shouldn't with my global config
- [BUG] Agent window focus lost after navigating with arrow keys, causing scroll deadlock
- [BUG] `--model` flag silently ignored in interactive sessions (works in `--print` only)
- [BUG] Dispatch permanently shows "desktop appears offline" on Windows 11 - never worked on first use
- feat: support per-command enableWeakerNetworkIsolation as safer alternative to dangerouslyDisableSandbox
- /code-review outputs a raw JSON array instead of readable findings
- [BUG] Cowork — Additional allowed domains ignored on Team plan; same domain works on Pro plan
- Haiku
- [Bug] False positive blocking beneficial outcomes in tool execution
- 3P Bedrock SSO: credentials silently expire without triggering re-auth on day 2+
- CLAUDE_AUTOCOMPACT_PCT_OVERRIDE in settings.json env block silently ignored by autocompact logic
- Auto-compaction deletes main session JSONL before verifying summary completion, causing data loss
- [Bug] Claude Code not executing stated actions or producing expected results
- [FEATURE] Deferred Messages — Queue Input for End of Turn
- [BUG] Up/Down arrows in input box navigate history instead of moving cursor — regression in 2.1.149+
- Cancelling a parallel tool-call batch corrupts thinking blocks -> 400 "thinking blocks cannot be modified" permanently wedges the session
- Claude Code caused data loss, then contradicted itself about recovery (two incidents, one session)
- [Bug] Unclear error messages from Claude Code CLI
- [Bug] Agent tool rejecting due to context size limit exceeded
- claude agents: daemon and bg-spare processes spin at ~100% CPU when idle
- [BUG] Compaction fails with "context window limit" error even when context usage is low (e.g., 20%) — regression in v2.1.153
- Remote Control entitlement lost after May 27-28 incident — `Error: Remote Control is not yet enabled for your account` on active Max subscription
- PreToolUse hook exit code 2 does not block Write tool
- [Bug] Thinking blocks in latest assistant message are immutable
- GUI: dispatch file:// and custom-scheme clicks to OS shell handler
- Show current model in statusLine by default
- [Bug] Agent console becomes unresponsive to keyboard input after multiple agents initialized
- [FEATURE] PreToolUse hooks should have a way of updating the environment
- [Bug] Unable to start or use Claude Code CLI
- [BUG] Repository not visible in Claude Code web repo picker
- Session permanently wedged on 400 "thinking blocks cannot be modified" after parallel tool_results
- [Bug] @ autocomplete loses sibling repos after a file edit in multi-repo workspace
- Unclear error message when creating sub-agent without authentication
- [Bug] Anthropic API errors causing frequent failures and high token usage
- [BUG] @ mention file picker only shows packages, not individual files (desktop app - Code tab)
- [Bug] TUI panel footer remains sticky and consumes excessive terminal space
- PR-status polling exhausts GitHub GraphQL rate limit on repos with many open PRs
- [BUG] Windows: welcome panel not shown in some project folders (2.1.153)
- [Bug] Anthropic API Error: thinking blocks corrupted during context compaction with extended thinking enabled
- API 400 "thinking blocks cannot be modified" permanently bricks session during agent activation (interleaved thinking + tool use)
- Right-click Copy copies the whole message instead of the selection; pasted text retains dark background
- Mid-session model switch corrupts conversation when extended thinking is enabled (API 400: 'thinking blocks cannot be modified')
- [BUG] Markdown file links in chat output do not open files when clicked (VS Code extension)
- Stuck retry loop: `400 thinking blocks cannot be modified` on large interleaved-thinking turns using AskUserQuestion
- [FEATURE] Prompt user for approval before auto-compaction proceeds
- Custom MCP connectors not attachable to scheduled routines — no UUID discovery path
- [BUG] Claude in Chrome — Navigation blocked for teams.cloud.microsoft and outlook.cloud.microsoft after Microsoft domain migration**
- [BUG] Claude Desktop — Personal plugins panel renders list but is entirely non-interactive (macOS, v1.9255.2)
- [Bug] error when using Workflows
- [BUG] Persistent "update available" notification despite being on latest version
- [BUG] Sweep Agent from /code-review never completes
- [Bug] Tool calls not executing or returning results
- [FEATURE] Cloud-synced memory and settings across machines
- [Bug] Terminal UI freezes when Ctrl+O view exits during interactive prompt in plan mode
- Continuous api errors when using claude code with Opus 4.7 with thinking on low
- [Feature Request] Add support for installing and using previous Claude Code versions
- [Bug] Extended Thinking: Summarized thinking blocks fail signature validation when resent to API
- [Bug] Anthropic API Error: 'thinking' blocks cannot be modified
- [Bug] Anthropic API Error: Thinking blocks cannot be modified with extended thinking mode
- Feature request: Lazy/on-demand MCP server connections
- [Bug] Tool Arguments Parsed as String Instead of Object
- [Bug] Anthropic API Error: Insufficient context provided
- [Bug] Claude Opus occasionally uses moskovian(russian) orthography instead of Ukrainian in system-prompted responses
- Opus 4.8: backgrounded task completions (subagents AND Bash) crash with 400 "thinking blocks cannot be modified"
- [Bug] Opus 4.7 fabricates stable preferences ("my default") to rationalize arbitrary choices when challenged
- [Bug] Unable to update Claude Code CLI
- [BUG] Desktop app: /remote-control mints link + connects bridge (main.log) but in-chat link/QR panel never renders
- Feature: sessionColor and sessionName in .claude/settings.json
- [BUG] Anthropic API error: thinking blocks
- [FEATURE] Support Remote MCPs in Cowork as in Claude Code
- [Bug] Anthropic API Error: 400 Bad Request with Redacted Thinking - 0 4.7 & 4.8
- [Bug] Anthropic API Error: Cannot modify thinking blocks from different model versions
- Interleaved thinking + multi-tool turn corrupts thinking block (text blanked, signature kept) → permanent 400 'blocks must remain as they were'
- [BUG] Mode/permission changes mid-tool-loop (effortLevel: xhigh) poisons entire session
- Session failure log: Opus 4.6 ignores its own rules for an entire session
- [BUG] "400 Guardrail was enabled" error when using Claude Opus 4.8 with AWS Bedrock
- [Feature Request] Add subagent approach selection option to avoid accidental feedback
- Persistent 400 'thinking blocks in the latest assistant message cannot be modified' — interleaved thinking persisted with empty text + signature bricks sessions
- [BUG] DesktopvsApp
- [BUG] Opus 4.7 cache hit rate collapse after May 27 incident — Messages 1.1k→88.9k in 9 minutes, $630/session
- [Bug] Anthropic API Error: Invalid thinking block format
- [BUG] FUCK CLAUDE
- Opus 4.8 extended thinking: Stop hook block re-entry corrupts thinking blocks → 400
- [Bug] 4.8 Fails when accessing previous model history
- [Bug] Unintended File Modifications During Execution
- [DOCS] Model configuration docs omit lean system prompt default scope and model exceptions
- Add "Always allow globally" option to permission prompts
- Server-side model upgrade (Opus 4.7→4.8) wedges in-flight sessions with `thinking blocks cannot be modified` 400
- [DOCS] AskUserQuestion docs missing multiple-choice prompt decision threshold
- [DOCS] Agent view docs omit shell-command background session launch syntax
- [DOCS] Agent view dispatch input docs incorrectly imply `/logout` dispatches as a prompt
- [DOCS] Claude in Chrome docs omit connected-browser selection behavior
- [DOCS] Plugin docs omit `defaultEnabled: false` for opt-in plugins
- Feature Request: Customizable chat text colors for user and assistant messages
- [DOCS] `/plugin` Discover tab docs omit directory-based suggested plugin pins
- VSCode Chrome integration silently fails: 3 distinct bugs
- [DOCS] MCP stdio docs omit session environment variables
- [Bug] Anthropic API error on second request within session with Claude Opus 4.8
- Cowork emits a blank session "index" handoff on focus when a CLI session is paused awaiting input
- [DOCS] MCP docs omit `claude mcp list/get` pending-approval output for unapproved project servers
- [BUG] /compact fails with 400 error when last assistant turn contains thinking blocks
- [DOCS] `/claude-api` docs omit Opus 4.8 migration guidance
- [DOCS] Fast mode docs still recommend deprecated Opus 4.6 override variable
- [DOCS] Bash tool docs omit `$TMPDIR` consistency across sandboxed and unsandboxed commands
- [Bug] Anthropic API Error: 400 Bad Request on Extended Thinking
- [DOCS] Background session docs omit worktree-isolation behavior for spawned subagents
- Built-in mechanistic self-verification of verifiable claims (symmetric to the auto permission gate)
- [DOCS] Worktree docs do not clarify `worktree.baseRef: "head"` inside linked worktrees
- [BUG] Excessive RAM usage with multiple parallel chats (~10 sessions → 30 GB memory pressure, macOS OOM)
- [DOCS] Managed MCP policy docs omit invalid `allowedMcpServers`/`deniedMcpServers` entry behavior
- [DOCS] Effort docs omit `CLAUDE_CODE_ALWAYS_ENABLE_EFFORT` unsupported-model behavior
- Regression (2.1.147–2.1.150?): resuming an extended-thinking session after a CC update/model-switch → unrecoverable 400, session bricked
- [DOCS] Windows updater docs omit `claude.exe` in-use recovery guidance
- [DOCS] VS Code auto mode docs still tie mode-picker visibility to bypass-permissions setting
- [DOCS] MCP docs omit `/mcp` tool list and detail rendering behavior
- [DOCS] Fine-grained tool streaming docs still describe provider opt-in behavior
- bypassPermissions: session startup reads flat pref, GUI toggle writes per-account pref — they never sync
- [BUG] Claude Desktop Code tab causes disk write limit violation — 8.5GB in 11 min, macOS kills app (M5, v1.9659.1)
- Ultrareview v2.1.96: docs describe /tasks command + claude ultrareview --json subcommand that don't exist; findings hard to read after completion
- I'd be happy to help create a GitHub issue title, but I don't see the error message in your message. Could you please share the specific error you're encountering? That way I can generate an accurate and descriptive issue title for you.
- [BUG] Claude in Chrome `file_upload` rejects all scheduled-task sessions with misleading error (real cause: INVALID_SESSION)
- Extended thinking: signed thinking block 'cannot be modified' (400) permanently wedges session
- RTL text support for Hebrew (and Arabic) in Claude Code
- [Bug] Random errors occurring across multiple operations