Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [Usage]: KeyError: 'layers.0.mlp.experts.w13_bias' when running quantized model on vLLM

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…

Error Message

I'm getting the following error when trying to serve a quantized model through vLLM. Tried v0.18 and v0.19 All the cases showed the same error. Am I doing something wrong? (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/gpt_oss.py", line 1225, in load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] return loader.load_weights(weights, mapper=self.hf_to_vllm_mapper) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/model_loader/reload/torchao_decorator.py", line 50, in patched_model_load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] return original_load_weights(self, weights, *args, **kwargs) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/utils.py", line 355, in load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] autoloaded_weights = set(self._load_module("", self.module, weights)) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/utils.py", line 302, in _load_module (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] yield from self._load_module( (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/utils.py", line 275, in _load_module (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] loaded_params = module_load_weights(weights) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/gpt_oss.py", line 1136, in load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] return self._load_weights_other( (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/gpt_oss.py", line 1045, in _load_weights_other (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] param = params_dict[name] (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ~~~~~~~~~~~^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] KeyError: 'layers.0.mlp.experts.w13_bias'

Fix Action

Fix / Workaround

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

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): 384 On-line CPU(s) list: 0-383 Vendor ID: AuthenticAMD Model name: AMD EPYC 9B45 CPU family: 26 Model: 2 Thread(s) per core: 2 Core(s) per socket: 96 Socket(s): 2 Stepping: 1 BogoMIPS: 5399.99 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 nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext mwaitx ssbd ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 clzero xsaveerptr wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid movdiri movdir64b avx512_vp2intersect flush_l1d Hypervisor vendor: KVM Virtualization type: full L1d cache: 9 MiB (192 instances) L1i cache: 6 MiB (192 instances) L2 cache: 192 MiB (192 instances) L3 cache: 768 MiB (24 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-95,192-287 NUMA node1 CPU(s): 96-191,288-383 Vulnerability Gather data sampling: 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 Reg file data sampling: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Mitigation; IBPB on VMEXIT only 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: Not affected

Loading safetensors checkpoint shards: 1% Completed | 1/73 [00:20<25:09, 20.96s/it] (Worker_TP0 pid=624) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/gpt_oss.py", line 1225, in load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] return loader.load_weights(weights, mapper=self.hf_to_vllm_mapper) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/model_loader/reload/torchao_decorator.py", line 50, in patched_model_load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] return original_load_weights(self, weights, *args, **kwargs) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/utils.py", line 355, in load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] autoloaded_weights = set(self._load_module("", self.module, weights)) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/utils.py", line 302, in _load_module (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] yield from self._load_module( (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/utils.py", line 275, in _load_module (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] loaded_params = module_load_weights(weights) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/gpt_oss.py", line 1136, in load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] return self._load_weights_other( (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/gpt_oss.py", line 1045, in _load_weights_other (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] param = params_dict[name] (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ~~~~~~~~~~~^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] KeyError: 'layers.0.mlp.experts.w13_bias'

Code Example

The output of `python collect_env.py`

Collecting environment information...
==============================
        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-6.12.68+-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 : Could not collect
Nvidia driver version        : Could not collect
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:                           52 bits physical, 57 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  384
On-line CPU(s) list:                     0-383
Vendor ID:                               AuthenticAMD
Model name:                              AMD EPYC 9B45
CPU family:                              26
Model:                                   2
Thread(s) per core:                      2
Core(s) per socket:                      96
Socket(s):                               2
Stepping:                                1
BogoMIPS:                                5399.99
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 nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext mwaitx ssbd ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 clzero xsaveerptr wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid movdiri movdir64b avx512_vp2intersect flush_l1d
Hypervisor vendor:                       KVM
Virtualization type:                     full
L1d cache:                               9 MiB (192 instances)
L1i cache:                               6 MiB (192 instances)
L2 cache:                                192 MiB (192 instances)
L3 cache:                                768 MiB (24 instances)
NUMA node(s):                            2
NUMA node0 CPU(s):                       0-95,192-287
NUMA node1 CPU(s):                       96-191,288-383
Vulnerability Gather data sampling:      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 Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Mitigation; IBPB on VMEXIT only
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:                   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==13.595.45
[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==4.57.6
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.19.0
vLLM Build Flags:
  CUDA Archs: 7.0 7.5 8.0 8.9 9.0 10.0 12.0; ROCm: Disabled
GPU Topology:
  Could not collect

==============================
     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
NCCL_P2P_LEVEL=SYS
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
RAW_BUFFERClick to expand / collapse

Your current environment

The output of `python collect_env.py`

Collecting environment information...
==============================
        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-6.12.68+-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 : Could not collect
Nvidia driver version        : Could not collect
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:                           52 bits physical, 57 bits virtual
Byte Order:                              Little Endian
CPU(s):                                  384
On-line CPU(s) list:                     0-383
Vendor ID:                               AuthenticAMD
Model name:                              AMD EPYC 9B45
CPU family:                              26
Model:                                   2
Thread(s) per core:                      2
Core(s) per socket:                      96
Socket(s):                               2
Stepping:                                1
BogoMIPS:                                5399.99
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 nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext mwaitx ssbd ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 clzero xsaveerptr wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid movdiri movdir64b avx512_vp2intersect flush_l1d
Hypervisor vendor:                       KVM
Virtualization type:                     full
L1d cache:                               9 MiB (192 instances)
L1i cache:                               6 MiB (192 instances)
L2 cache:                                192 MiB (192 instances)
L3 cache:                                768 MiB (24 instances)
NUMA node(s):                            2
NUMA node0 CPU(s):                       0-95,192-287
NUMA node1 CPU(s):                       96-191,288-383
Vulnerability Gather data sampling:      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 Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Mitigation; IBPB on VMEXIT only
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:                   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==13.595.45
[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==4.57.6
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.19.0
vLLM Build Flags:
  CUDA Archs: 7.0 7.5 8.0 8.9 9.0 10.0 12.0; ROCm: Disabled
GPU Topology:
  Could not collect

==============================
     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
NCCL_P2P_LEVEL=SYS
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

How would you like to use vllm

I'm getting the following error when trying to serve a quantized model through vLLM. Tried v0.18 and v0.19

Tried: TevunahAi/gpt-oss-120b-1024-Calibration-FP8 unsloth/gpt-oss-120b-unsloth-bnb-4bit and a model I quantized using llm-compressor all presented the same behavior.

For TevunahAi I tried running it with just these params:

vllm serve TevunahAi/gpt-oss-120b-1024-Calibration-FP8
--dtype auto
--max-model-len 8192

All the cases showed the same error. Am I doing something wrong?

Loading safetensors checkpoint shards: 1% Completed | 1/73 [00:20<25:09, 20.96s/it] (Worker_TP0 pid=624) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/gpt_oss.py", line 1225, in load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] return loader.load_weights(weights, mapper=self.hf_to_vllm_mapper) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/model_loader/reload/torchao_decorator.py", line 50, in patched_model_load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] return original_load_weights(self, weights, *args, **kwargs) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/utils.py", line 355, in load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] autoloaded_weights = set(self._load_module("", self.module, weights)) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/utils.py", line 302, in _load_module (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] yield from self._load_module( (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/utils.py", line 275, in _load_module (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] loaded_params = module_load_weights(weights) (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/gpt_oss.py", line 1136, in load_weights (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] return self._load_weights_other( (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/models/gpt_oss.py", line 1045, in _load_weights_other (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] param = params_dict[name] (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] ~~~~~~~~~~~^^^^^^ (Worker_TP0 pid=624) ERROR 04-19 16:21:20 [multiproc_executor.py:857] KeyError: 'layers.0.mlp.experts.w13_bias'

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

TL;DR

The error is likely due to a mismatch between the model architecture and the weights being loaded, specifically a missing 'layers.0.mlp.experts.w13_bias' parameter.

Guidance

  1. Verify model architecture: Check the model architecture of the quantized models (TevunahAi/gpt-oss-120b-1024-Calibration-FP8, unsloth/gpt-oss-120b-unsloth-bnb-4bit, and the custom quantized model) to ensure they match the expected architecture.
  2. Check weights file: Inspect the weights file being loaded to confirm that it contains the 'layers.0.mlp.experts.w13_bias' parameter.
  3. Model compatibility: Ensure that the models are compatible with the vLLM version being used (v0.18 and v0.19).
  4. Quantization process: Review the quantization process used to create the custom quantized model to ensure it was done correctly.

Example

No code snippet is provided as the issue seems to be related to model architecture and weights compatibility.

Notes

The error message suggests a KeyError, which typically indicates a missing key in a dictionary. In this case, the missing key is 'layers.0.mlp.experts.w13_bias'. This could be due to a mismatch between the model architecture and the weights being loaded.

Recommendation

Apply a workaround by checking the model architecture and weights compatibility before loading the model. If the issue persists, consider upgrading to a newer version of vLLM or seeking further assistance from the vLLM community.

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#environment variable#authentication setup#request error#file not found

Still need to ship something?

×6

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

Back to top recommendations

TRENDING

vllm - 💡(How to fix) Fix [Usage]: KeyError: 'layers.0.mlp.experts.w13_bias' when running quantized model on vLLM