Issue Station
Sign In
Tools hereToolbox

pytorch - 💡(How to fix) Fix [Symmetric Memory] symm buffer init and rendezvous cannot be assigned to a specific CUDA stream [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities 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

Loading…
GitHub stats
pytorch/pytorch#181086•Fetched 2026-04-23 07:22:45
View on GitHub
Comments
0
Participants
1
Timeline
41
Reactions
0
Author
leeeizhangleeeizhang
Participants
leeeizhangleeeizhang
Timeline (top)
mentioned ×13subscribed ×13unsubscribed ×13labeled ×2

Fix Action

Fix / Workaround

CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 46 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 128 On-line CPU(s) list: 0-127 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Platinum 8336C CPU @ 2.30GHz CPU family: 6 Model: 106 Thread(s) per core: 2 Core(s) per socket: 32 Socket(s): 2 Stepping: 6 CPU(s) scaling MHz: 27% CPU max MHz: 3500.0000 CPU min MHz: 800.0000 BogoMIPS: 4600.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 invpcid_single intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid fsrm md_clear pconfig flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 3 MiB (64 instances) L1i cache: 2 MiB (64 instances) L2 cache: 80 MiB (64 instances) L3 cache: 108 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-31,64-95 NUMA node1 CPU(s): 32-63,96-127 Vulnerability Gather data sampling: Vulnerable: No microcode Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode; SMT vulnerable Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

Code Example

import torch
import torch.distributed as dist
import torch.distributed._symmetric_memory as symm_mem


def _symm_all_gather_into_tensor(tensor_for_comm, group):
    rank = dist.get_rank(group)
    group_size = dist.get_world_size(group)

    symm_buf = symm_mem.empty(
        [group_size, *allgather_tensor.shape],
        dtype=allgather_tensor.dtype,
        device=allgather_tensor.device,
    )
    hdl = symm_mem.rendezvous(symm_buf, group)

    for step in range(group_size):
        target_rank = (rank + step) % group_size
        remote_full_buf = hdl.get_buffer(target_rank, symm_buf.shape, symm_buf.dtype)
        target_chunk = remote_full_buf.chunk(group_size, dim=0)[rank]
        target_chunk.copy_(tensor_for_comm)
    hdl.barrier(channel=0)

    output = torch.empty_like(symm_buf)
    output.copy_(symm_buf)
    return output


def symm_all_gather_into_tensor(tensor_for_comm, group):
    with torch.profiler.record_function("symm_all_gather_into_tensor"):
        return _symm_all_gather_into_tensor(tensor_for_comm, group)


def setup_dist():
    dist.init_process_group(backend="cpu:gloo,cuda:nccl")
    torch.manual_seed(42)
    torch.cuda.manual_seed(42)
    torch.cuda.set_device(dist.get_rank() % torch.cuda.device_count())
    torch.set_default_dtype(torch.bfloat16)


if __name__ == "__main__":
    """
    torchrun --nproc_per_node=2 test.py
    """
    setup_dist()

    stream, group = torch.cuda.Stream(), dist.new_group()

    allgather_tensor = torch.empty(
        (2, 32, 1024, 1024),
        dtype=torch.bfloat16,
        device="cuda",
    )

    with torch.profiler.profile(
        activities=[
            torch.profiler.ProfilerActivity.CPU,
            torch.profiler.ProfilerActivity.CUDA,
        ],
        schedule=torch.profiler.schedule(wait=0, warmup=1, active=9, repeat=0),
        on_trace_ready=torch.profiler.tensorboard_trace_handler('_timeline'),
        record_shapes=True,
        with_stack=True,
        with_flops=True,
    ) as p:
        for _ in range(10):
            torch.cuda.synchronize()

            with torch.cuda.stream(stream):
                _ = symm_all_gather_into_tensor(allgather_tensor, group)

            torch.cuda.synchronize()
            p.step()

---

Collecting environment information...
PyTorch version: 2.11.0+cu126
Is debug build: False
CUDA used to build PyTorch: 12.6
ROCM used to build PyTorch: N/A

OS: Debian GNU/Linux 12 (bookworm) (x86_64)
GCC version: (conda-forge gcc 14.3.0-18) 14.3.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.36

Python version: 3.11.14 | packaged by conda-forge | (main, Oct 22 2025, 22:46:25) [GCC 14.3.0] (64-bit runtime)
Python platform: Linux-5.15.152.bsk.9-amd64-x86_64-with-glibc2.36
Is CUDA available: True
CUDA runtime version: 12.9.86
CUDA_MODULE_LOADING set to: 
GPU models and configuration: 
GPU 0: NVIDIA A100-SXM4-80GB
GPU 1: NVIDIA A100-SXM4-80GB
GPU 2: NVIDIA A100-SXM4-80GB
GPU 3: NVIDIA A100-SXM4-80GB
GPU 4: NVIDIA A100-SXM4-80GB
GPU 5: NVIDIA A100-SXM4-80GB
GPU 6: NVIDIA A100-SXM4-80GB
GPU 7: NVIDIA A100-SXM4-80GB

Nvidia driver version: 535.161.08
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:                      46 bits physical, 57 bits virtual
Byte Order:                         Little Endian
CPU(s):                             128
On-line CPU(s) list:                0-127
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Platinum 8336C CPU @ 2.30GHz
CPU family:                         6
Model:                              106
Thread(s) per core:                 2
Core(s) per socket:                 32
Socket(s):                          2
Stepping:                           6
CPU(s) scaling MHz:                 27%
CPU max MHz:                        3500.0000
CPU min MHz:                        800.0000
BogoMIPS:                           4600.00
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 invpcid_single intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization:                     VT-x
L1d cache:                          3 MiB (64 instances)
L1i cache:                          2 MiB (64 instances)
L2 cache:                           80 MiB (64 instances)
L3 cache:                           108 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-31,64-95
NUMA node1 CPU(s):                  32-63,96-127
Vulnerability Gather data sampling: Vulnerable: No microcode
Vulnerability Itlb multihit:        Not affected
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Vulnerable: Clear CPU buffers attempted, no microcode; SMT vulnerable
Vulnerability Retbleed:             Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:           Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Not affected

Versions of relevant libraries:
[pip3] mypy_extensions==1.1.0
[pip3] numpy==2.4.3
[pip3] nvidia-cublas==13.1.0.3
[pip3] nvidia-cublas-cu12==12.6.4.1
[pip3] nvidia-cuda-cupti==13.0.85
[pip3] nvidia-cuda-cupti-cu12==12.6.80
[pip3] nvidia-cuda-nvrtc==13.0.88
[pip3] nvidia-cuda-nvrtc-cu12==12.6.85
[pip3] nvidia-cuda-runtime==13.0.96
[pip3] nvidia-cuda-runtime-cu12==12.6.77
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-cu13==9.19.0.56
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-cufft-cu12==11.3.0.4
[pip3] nvidia-curand==10.4.0.35
[pip3] nvidia-curand-cu12==10.3.7.77
[pip3] nvidia-cusolver==12.0.4.66
[pip3] nvidia-cusolver-cu12==11.7.1.2
[pip3] nvidia-cusparse==12.6.3.3
[pip3] nvidia-cusparse-cu12==12.5.4.2
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-cusparselt-cu13==0.8.0
[pip3] nvidia-nccl-cu12==2.28.9
[pip3] nvidia-nccl-cu13==2.28.9
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvtx==13.0.85
[pip3] nvidia-nvtx-cu12==12.6.77
[pip3] optree==0.19.0
[pip3] torch==2.11.0+cu126
[pip3] torchvision==0.26.0+cu126
[pip3] triton==3.6.0
RAW_BUFFERClick to expand / collapse

🐛 Describe the bug

I implemented symm_mem-based communication, but I found that some symm_mem APIs (symm_mem.empty and symm_mem.rendezvous) could not assigned to a specific cuda stream, even i have set the execution under the context bound to a specific CUDA stream. Nevertheless, merely memCpy and symm_mem::barrier are executed in this CUDA stream, while other initialized symm_mem operations take place in the default CUDA stream.

<img width="2390" height="906" alt="Image" src="https://github.com/user-attachments/assets/8d010fab-c006-491e-a2e9-fcdaea2029d6" />

Reproduce codes:

import torch
import torch.distributed as dist
import torch.distributed._symmetric_memory as symm_mem


def _symm_all_gather_into_tensor(tensor_for_comm, group):
    rank = dist.get_rank(group)
    group_size = dist.get_world_size(group)

    symm_buf = symm_mem.empty(
        [group_size, *allgather_tensor.shape],
        dtype=allgather_tensor.dtype,
        device=allgather_tensor.device,
    )
    hdl = symm_mem.rendezvous(symm_buf, group)

    for step in range(group_size):
        target_rank = (rank + step) % group_size
        remote_full_buf = hdl.get_buffer(target_rank, symm_buf.shape, symm_buf.dtype)
        target_chunk = remote_full_buf.chunk(group_size, dim=0)[rank]
        target_chunk.copy_(tensor_for_comm)
    hdl.barrier(channel=0)

    output = torch.empty_like(symm_buf)
    output.copy_(symm_buf)
    return output


def symm_all_gather_into_tensor(tensor_for_comm, group):
    with torch.profiler.record_function("symm_all_gather_into_tensor"):
        return _symm_all_gather_into_tensor(tensor_for_comm, group)


def setup_dist():
    dist.init_process_group(backend="cpu:gloo,cuda:nccl")
    torch.manual_seed(42)
    torch.cuda.manual_seed(42)
    torch.cuda.set_device(dist.get_rank() % torch.cuda.device_count())
    torch.set_default_dtype(torch.bfloat16)


if __name__ == "__main__":
    """
    torchrun --nproc_per_node=2 test.py
    """
    setup_dist()

    stream, group = torch.cuda.Stream(), dist.new_group()

    allgather_tensor = torch.empty(
        (2, 32, 1024, 1024),
        dtype=torch.bfloat16,
        device="cuda",
    )

    with torch.profiler.profile(
        activities=[
            torch.profiler.ProfilerActivity.CPU,
            torch.profiler.ProfilerActivity.CUDA,
        ],
        schedule=torch.profiler.schedule(wait=0, warmup=1, active=9, repeat=0),
        on_trace_ready=torch.profiler.tensorboard_trace_handler('_timeline'),
        record_shapes=True,
        with_stack=True,
        with_flops=True,
    ) as p:
        for _ in range(10):
            torch.cuda.synchronize()

            with torch.cuda.stream(stream):
                _ = symm_all_gather_into_tensor(allgather_tensor, group)

            torch.cuda.synchronize()
            p.step()

Versions

Collecting environment information...
PyTorch version: 2.11.0+cu126
Is debug build: False
CUDA used to build PyTorch: 12.6
ROCM used to build PyTorch: N/A

OS: Debian GNU/Linux 12 (bookworm) (x86_64)
GCC version: (conda-forge gcc 14.3.0-18) 14.3.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.36

Python version: 3.11.14 | packaged by conda-forge | (main, Oct 22 2025, 22:46:25) [GCC 14.3.0] (64-bit runtime)
Python platform: Linux-5.15.152.bsk.9-amd64-x86_64-with-glibc2.36
Is CUDA available: True
CUDA runtime version: 12.9.86
CUDA_MODULE_LOADING set to: 
GPU models and configuration: 
GPU 0: NVIDIA A100-SXM4-80GB
GPU 1: NVIDIA A100-SXM4-80GB
GPU 2: NVIDIA A100-SXM4-80GB
GPU 3: NVIDIA A100-SXM4-80GB
GPU 4: NVIDIA A100-SXM4-80GB
GPU 5: NVIDIA A100-SXM4-80GB
GPU 6: NVIDIA A100-SXM4-80GB
GPU 7: NVIDIA A100-SXM4-80GB

Nvidia driver version: 535.161.08
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:                      46 bits physical, 57 bits virtual
Byte Order:                         Little Endian
CPU(s):                             128
On-line CPU(s) list:                0-127
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Platinum 8336C CPU @ 2.30GHz
CPU family:                         6
Model:                              106
Thread(s) per core:                 2
Core(s) per socket:                 32
Socket(s):                          2
Stepping:                           6
CPU(s) scaling MHz:                 27%
CPU max MHz:                        3500.0000
CPU min MHz:                        800.0000
BogoMIPS:                           4600.00
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 invpcid_single intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization:                     VT-x
L1d cache:                          3 MiB (64 instances)
L1i cache:                          2 MiB (64 instances)
L2 cache:                           80 MiB (64 instances)
L3 cache:                           108 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-31,64-95
NUMA node1 CPU(s):                  32-63,96-127
Vulnerability Gather data sampling: Vulnerable: No microcode
Vulnerability Itlb multihit:        Not affected
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Vulnerable: Clear CPU buffers attempted, no microcode; SMT vulnerable
Vulnerability Retbleed:             Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:           Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Not affected

Versions of relevant libraries:
[pip3] mypy_extensions==1.1.0
[pip3] numpy==2.4.3
[pip3] nvidia-cublas==13.1.0.3
[pip3] nvidia-cublas-cu12==12.6.4.1
[pip3] nvidia-cuda-cupti==13.0.85
[pip3] nvidia-cuda-cupti-cu12==12.6.80
[pip3] nvidia-cuda-nvrtc==13.0.88
[pip3] nvidia-cuda-nvrtc-cu12==12.6.85
[pip3] nvidia-cuda-runtime==13.0.96
[pip3] nvidia-cuda-runtime-cu12==12.6.77
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-cu13==9.19.0.56
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-cufft-cu12==11.3.0.4
[pip3] nvidia-curand==10.4.0.35
[pip3] nvidia-curand-cu12==10.3.7.77
[pip3] nvidia-cusolver==12.0.4.66
[pip3] nvidia-cusolver-cu12==11.7.1.2
[pip3] nvidia-cusparse==12.6.3.3
[pip3] nvidia-cusparse-cu12==12.5.4.2
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-cusparselt-cu13==0.8.0
[pip3] nvidia-nccl-cu12==2.28.9
[pip3] nvidia-nccl-cu13==2.28.9
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvtx==13.0.85
[pip3] nvidia-nvtx-cu12==12.6.77
[pip3] optree==0.19.0
[pip3] torch==2.11.0+cu126
[pip3] torchvision==0.26.0+cu126
[pip3] triton==3.6.0

extent analysis

TL;DR

The issue can be resolved by ensuring that the symm_mem.empty and symm_mem.rendezvous operations are properly bound to the specified CUDA stream.

Guidance

  • Verify that the CUDA stream is correctly set before calling symm_mem.empty and symm_mem.rendezvous by checking the current stream using torch.cuda.current_stream().
  • Ensure that the symm_mem.empty and symm_mem.rendezvous operations are executed within the context of the specified CUDA stream using with torch.cuda.stream(stream):.
  • Check the documentation of symm_mem.empty and symm_mem.rendezvous to see if there are any specific requirements or limitations for executing these operations on a specific CUDA stream.
  • Use the torch.profiler to profile the execution of the symm_all_gather_into_tensor function and verify that the symm_mem.empty and symm_mem.rendezvous operations are being executed on the correct CUDA stream.

Example

with torch.cuda.stream(stream):
    symm_buf = symm_mem.empty(
        [group_size, *allgather_tensor.shape],
        dtype=allgather_tensor.dtype,
        device=allgather_tensor.device,
    )
    hdl = symm_mem.rendezvous(symm_buf, group)

Notes

The issue may be related to the fact that symm_mem.empty and symm_mem.rendezvous are not properly bound to the specified CUDA stream. By ensuring that these operations are executed within the context of the correct stream, the issue may be resolved.

Recommendation

Apply workaround: Ensure that symm_mem.empty and symm_mem.rendezvous are executed within the context of the specified CUDA stream. This can be done by using the with torch.cuda.stream(stream): context manager to set the current stream before calling these operations.

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?
Loading…
#api#output truncation#response parsing#generation error#database connection

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING