Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [Bug]: AssertionError: assert num_kv_heads == 1 with CPU KV Offloading + GLM-5-FP8 [1 comments, 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
vllm-project/vllm#37404•Fetched 2026-04-08 00:57:39
View on GitHub
Comments
1
Participants
1
Timeline
3
Reactions
0
Author
yz342yz342
Participants
yz342yz342
Timeline (top)
closed ×1commented ×1labeled ×1

Error Message

(Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] WorkerProc hit an exception. (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] Traceback (most recent call last): (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/multiproc_executor.py", line 927, in worker_busy_loop (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] output = func(*args, **kwargs) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 306, in initialize_from_config (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self.worker.initialize_from_config(kv_cache_config) # type: ignore (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/tracing/otel.py", line 178, in sync_wrapper (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] return func(*args, **kwargs) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py", line 553, in initialize_from_config (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self.model_runner.initialize_kv_cache(kv_cache_config) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 6518, in initialize_kv_cache (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] kv_transfer_group.register_kv_caches(kv_caches) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py", line 141, in register_kv_caches (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self.connector_worker.register_kv_caches(kv_caches) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py", line 612, in register_kv_caches (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self._register_handlers(kv_caches, attn_backends) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py", line 596, in _register_handlers (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] for src_cls, dst_cls, handler in self.spec.get_handlers( (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/kv_offload/cpu.py", line 118, in get_handlers (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self._handlers = CpuGpuOffloadingHandlers( (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/kv_offload/worker/cpu_gpu.py", line 242, in init (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] test_shape = attn_backend.get_kv_cache_shape( (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/attention/backends/mla/indexer.py", line 58, in get_kv_cache_shape (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] assert num_kv_heads == 1

Fix Action

Fix / Workaround

============================== CPU Info

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): 224 On-line CPU(s) list: 0-223 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Platinum 8480+ CPU family: 6 Model: 143 Thread(s) per core: 2 Core(s) per socket: 56 Socket(s): 2 Stepping: 8 BogoMIPS: 4000.00 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 tsc_known_freq pni pclmulqdq dtes64 monitor 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 cat_l2 cdp_l3 invpcid_single cdp_l2 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 avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 5.3 MiB (112 instances) L1i cache: 3.5 MiB (112 instances) L2 cache: 224 MiB (112 instances) L3 cache: 210 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126,128,130,132,134,136,138,140,142,144,146,148,150,152,154,156,158,160,162,164,166,168,170,172,174,176,178,180,182,184,186,188,190,192,194,196,198,200,202,204,206,208,210,212,214,216,218,220,222 NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127,129,131,133,135,137,139,141,143,145,147,149,151,153,155,157,159,161,163,165,167,169,171,173,175,177,179,181,183,185,187,189,191,193,195,197,199,201,203,205,207,209,211,213,215,217,219,221,223 Vulnerability Gather data sampling: 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 Reg file data sampling: Not affected 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 / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

Code Example

Your output of `python collect_env.py` here

---

vllm serve zai-org/GLM-5-FP8"
      --gpu-memory-utilization 0.85 \
      ---enable-auto-tool-choice \
      --tool-call-parser glm47 \
      --reasoning-parser glm45 \
      --default-chat-template-kwargs {"enable_thinking": false} \
      --tensor-parallel-size 8 \
      --performance-mode interactivity \
      --kv-offloading-size 1000 \
      --disable-hybrid-kv-cache-manager
RAW_BUFFERClick to expand / collapse

Your current environment

<details> using vllm-openai: nightly-54a62a79f70982742a227c845b96148e6401d0e7 <summary>The output of <code>python collect_env.py</code></summary> ============================== System Info ============================== OS : Ubuntu 22.04.5 LTS (x86_64) GCC version : (Ubuntu 11.4.0-1ubuntu1~22.04.3) 11.4.0 Clang version : Could not collect CMake version : Could not collect Libc version : glibc-2.35

============================== PyTorch Info

PyTorch version : 2.10.0+cu129 Is debug build : False CUDA used to build PyTorch : 12.9 ROCM used to build PyTorch : N/A

============================== Python Environment

Python version : 3.12.13 (main, Mar 4 2026, 09:23:07) [GCC 11.4.0] (64-bit runtime) Python platform : Linux-5.15.0-141-generic-x86_64-with-glibc2.35

============================== CUDA / GPU Info

Is CUDA available : True CUDA runtime version : 12.9.86 CUDA_MODULE_LOADING set to : GPU models and configuration : GPU 0: NVIDIA H200 GPU 1: NVIDIA H200 GPU 2: NVIDIA H200 GPU 3: NVIDIA H200 GPU 4: NVIDIA H200 GPU 5: NVIDIA H200 GPU 6: NVIDIA H200 GPU 7: NVIDIA H200

Nvidia driver version : 560.35.03 cuDNN version : Could not collect HIP runtime version : N/A MIOpen runtime version : N/A Is XNNPACK available : True

============================== CPU Info

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): 224 On-line CPU(s) list: 0-223 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Platinum 8480+ CPU family: 6 Model: 143 Thread(s) per core: 2 Core(s) per socket: 56 Socket(s): 2 Stepping: 8 BogoMIPS: 4000.00 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 tsc_known_freq pni pclmulqdq dtes64 monitor 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 cat_l2 cdp_l3 invpcid_single cdp_l2 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 avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 5.3 MiB (112 instances) L1i cache: 3.5 MiB (112 instances) L2 cache: 224 MiB (112 instances) L3 cache: 210 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126,128,130,132,134,136,138,140,142,144,146,148,150,152,154,156,158,160,162,164,166,168,170,172,174,176,178,180,182,184,186,188,190,192,194,196,198,200,202,204,206,208,210,212,214,216,218,220,222 NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127,129,131,133,135,137,139,141,143,145,147,149,151,153,155,157,159,161,163,165,167,169,171,173,175,177,179,181,183,185,187,189,191,193,195,197,199,201,203,205,207,209,211,213,215,217,219,221,223 Vulnerability Gather data sampling: 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 Reg file data sampling: Not affected 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 / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

============================== Versions of relevant libraries

[pip3] flashinfer-python==0.6.6 [pip3] numpy==2.2.6 [pip3] nvidia-cublas-cu12==12.9.1.4 [pip3] nvidia-cuda-cupti-cu12==12.9.79 [pip3] nvidia-cuda-nvrtc-cu12==12.9.86 [pip3] nvidia-cuda-runtime-cu12==12.9.79 [pip3] nvidia-cudnn-cu12==9.10.2.21 [pip3] nvidia-cudnn-frontend==1.18.0 [pip3] nvidia-cufft-cu12==11.4.1.4 [pip3] nvidia-cufile-cu12==1.14.1.1 [pip3] nvidia-curand-cu12==10.3.10.19 [pip3] nvidia-cusolver-cu12==11.7.5.82 [pip3] nvidia-cusparse-cu12==12.5.10.65 [pip3] nvidia-cusparselt-cu12==0.7.1 [pip3] nvidia-cutlass-dsl==4.4.2 [pip3] nvidia-cutlass-dsl-libs-base==4.4.2 [pip3] nvidia-ml-py==13.590.48 [pip3] nvidia-nccl-cu12==2.27.5 [pip3] nvidia-nvjitlink-cu12==12.9.86 [pip3] nvidia-nvshmem-cu12==3.4.5 [pip3] nvidia-nvtx-cu12==12.9.79 [pip3] pyzmq==27.1.0 [pip3] torch==2.10.0+cu129 [pip3] torch_c_dlpack_ext==0.1.5 [pip3] torchaudio==2.10.0+cu129 [pip3] torchvision==0.25.0+cu129 [pip3] transformers==5.3.0 [pip3] triton==3.6.0 [conda] Could not collect

============================== vLLM Info

ROCM Version : Could not collect vLLM Version : 0.17.2rc0 vLLM Build Flags: CUDA Archs: 7.0 7.5 8.0 8.9 9.0 10.0 12.0; ROCm: Disabled GPU Topology: GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 NIC9 CPU Affinity NUMA Affinity GPU NUMA ID GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 PIX NODE NODE NODE SYS SYS SYS SYS SYS SYS 0,2,4,6,8,10 0N/A GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 NODE PIX NODE NODE SYS SYS SYS SYS SYS SYS 0,2,4,6,8,10 0N/A GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 NODE NODE PIX NODE SYS SYS SYS SYS SYS SYS 0,2,4,6,8,10 0N/A GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 NODE NODE NODE PIX SYS SYS SYS SYS SYS SYS 0,2,4,6,8,10 0N/A GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS PIX PIX PIX NODE NODE NODE 1,3,5,7,9,11 1N/A GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS NODE NODE NODE PIX NODE NODE 1,3,5,7,9,11 1N/A GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS NODE NODE NODE NODE PIX NODE 1,3,5,7,9,11 1N/A GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS NODE NODE NODE NODE NODE PIX 1,3,5,7,9,11 1N/A NIC0 PIX NODE NODE NODE SYS SYS SYS SYS X NODE NODE NODE SYS SYS SYS SYS SYS SYS NIC1 NODE PIX NODE NODE SYS SYS SYS SYS NODE X NODE NODE SYS SYS SYS SYS SYS SYS NIC2 NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE X NODE SYS SYS SYS SYS SYS SYS NIC3 NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE X SYS SYS SYS SYS SYS SYS NIC4 SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS X PIX PIX NODE NODE NODE NIC5 SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS PIX X PIX NODE NODE NODE NIC6 SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS PIX PIX X NODE NODE NODE NIC7 SYS SYS SYS SYS NODE PIX NODE NODE SYS SYS SYS SYS NODE NODE NODE X NODE NODE NIC8 SYS SYS SYS SYS NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE NODE NODE X NODE NIC9 SYS SYS SYS SYS NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE NODE NODE X

Legend:

X = Self SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI) NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU) PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge) PIX = Connection traversing at most a single PCIe bridge NV# = Connection traversing a bonded set of # NVLinks

NIC Legend:

NIC0: mlx5_0 NIC1: mlx5_1 NIC2: mlx5_2 NIC3: mlx5_3 NIC4: mlx5_4 NIC5: mlx5_5 NIC6: mlx5_6 NIC7: mlx5_7 NIC8: mlx5_8 NIC9: mlx5_9

============================== Environment Variables

NVIDIA_VISIBLE_DEVICES=all NVIDIA_REQUIRE_CUDA=cuda>=12.9 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571 TORCH_CUDA_ARCH_LIST=7.0 7.5 8.0 8.9 9.0 10.0 12.0 NVIDIA_DRIVER_CAPABILITIES=compute,utility VLLM_USAGE_SOURCE=production-docker-image CUDA_VERSION=12.9.1 VLLM_ENABLE_CUDA_COMPATIBILITY=0 LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64 PYTORCH_NVML_BASED_CUDA_CHECK=1 TORCHINDUCTOR_COMPILE_THREADS=1 TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

Your output of `python collect_env.py` here
</details>

🐛 Describe the bug

vllm serve zai-org/GLM-5-FP8"
      --gpu-memory-utilization 0.85 \
      ---enable-auto-tool-choice \
      --tool-call-parser glm47 \
      --reasoning-parser glm45 \
      --default-chat-template-kwargs {"enable_thinking": false} \
      --tensor-parallel-size 8 \
      --performance-mode interactivity \
      --kv-offloading-size 1000 \
      --disable-hybrid-kv-cache-manager

AssertionError in mla/indexer.py when using kv_offloading_size with MLA attention model (GLM-5-FP8)

(Worker_TP6 pid=604) INFO 03-17 22:03:06 factory.py:51] Creating offloading spec with name: CPUOffloadingSpec (Worker_TP7 pid=605) WARNING 03-17 22:03:06 spec.py:25] Initializing OffloadingSpec. This API is experimental and subject to change in the future as we iterate the design. (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] WorkerProc hit an exception. (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] Traceback (most recent call last): (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/multiproc_executor.py", line 927, in worker_busy_loop (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] output = func(*args, **kwargs) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 306, in initialize_from_config (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self.worker.initialize_from_config(kv_cache_config) # type: ignore (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/tracing/otel.py", line 178, in sync_wrapper (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] return func(*args, **kwargs) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py", line 553, in initialize_from_config (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self.model_runner.initialize_kv_cache(kv_cache_config) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 6518, in initialize_kv_cache (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] kv_transfer_group.register_kv_caches(kv_caches) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py", line 141, in register_kv_caches (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self.connector_worker.register_kv_caches(kv_caches) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py", line 612, in register_kv_caches (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self._register_handlers(kv_caches, attn_backends) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py", line 596, in _register_handlers (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] for src_cls, dst_cls, handler in self.spec.get_handlers( (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/kv_offload/cpu.py", line 118, in get_handlers (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self._handlers = CpuGpuOffloadingHandlers( (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/kv_offload/worker/cpu_gpu.py", line 242, in init (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] test_shape = attn_backend.get_kv_cache_shape( (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/attention/backends/mla/indexer.py", line 58, in get_kv_cache_shape (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] assert num_kv_heads == 1 (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] AssertionError (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] Traceback (most recent call last): (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/multiproc_executor.py", line 927, in worker_busy_loop (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] output = func(*args, **kwargs) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/worker_base.py", line 306, in initialize_from_config (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self.worker.initialize_from_config(kv_cache_config) # type: ignore (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/tracing/otel.py", line 178, in sync_wrapper (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] return func(*args, **kwargs) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py", line 553, in initialize_from_config (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self.model_runner.initialize_kv_cache(kv_cache_config) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 6518, in initialize_kv_cache (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] kv_transfer_group.register_kv_caches(kv_caches) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py", line 141, in register_kv_caches (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self.connector_worker.register_kv_caches(kv_caches) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py", line 612, in register_kv_caches (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self._register_handlers(kv_caches, attn_backends) (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py", line 596, in _register_handlers (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] for src_cls, dst_cls, handler in self.spec.get_handlers( (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/kv_offload/cpu.py", line 118, in get_handlers (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] self._handlers = CpuGpuOffloadingHandlers( (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/kv_offload/worker/cpu_gpu.py", line 242, in init (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] test_shape = attn_backend.get_kv_cache_shape( (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/attention/backends/mla/indexer.py", line 58, in get_kv_cache_shape (Worker_TP4 pid=602) ERROR 03-17 22:03:06 multiproc_executor.py:932] assert num_kv_heads == 1

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

extent analysis

Fix Plan

The error occurs because the get_kv_cache_shape method in mla/indexer.py expects num_kv_heads to be 1, but it's not. To fix this, we need to modify the get_kv_cache_shape method to handle cases where num_kv_heads is not 1.

Here are the steps to fix the issue:

  • Modify the get_kv_cache_shape method in mla/indexer.py to remove the assertion that num_kv_heads must be 1.
  • Update the method to correctly calculate the KV cache shape for cases where num_kv_heads is not 1.

Example code:

# mla/indexer.py

def get_kv_cache_shape(self, num_kv_heads, seq_len, hidden_size):
    # Remove the assertion
    # assert num_kv_heads == 1
    
    # Calculate the KV cache shape
    kv_cache_shape = (num_kv_heads, seq_len, hidden_size)
    return kv_cache_shape

Verification

To verify that the fix worked, run the vllm serve command with the same arguments as before:

vllm serve zai-org/GLM-5-FP8 \
  --gpu-memory-utilization 0.85 \
  --enable-auto-tool-choice \
  --tool-call-parser glm47 \
  --reasoning-parser glm45 \
  --default-chat-template-kwargs {"enable_thinking": false} \
  --tensor-parallel-size 8 \
  --performance-mode interactivity \
  --kv-offloading-size 1000 \
  --disable-hybrid-kv-cache-manager

If the fix is correct, the command should run without errors.

Extra Tips

  • Make sure to test the fix thoroughly to ensure that it doesn't introduce any new issues.
  • Consider adding additional logging or debugging statements to help diagnose any future issues that may arise.
  • If you're still experiencing issues, try searching for relevant issues on the VLLM GitHub page or asking the chatbot for help.

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#ssr#installation#tensor shape#environment variable#model compatibility#GPU setup#container setup

Still need to ship something?

×6

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

Back to top recommendations

TRENDING