vllm - 💡(How to fix) Fix [Bug]: Qwen3-30B-A3B on B200 (TP=8) — K must be divisible by blockK in flashinfer convert_to_block_layout (unquantized MoE oracle path) [1 comments, 2 participants]

vllm2026-04-30 10:10:28

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.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

vllm-project/vllm#41360•Fetched 2026-05-01 05:34:01

View on GitHub

Comments

Participants

Timeline

Reactions

Author

huydhn

Participants

huydhn

yzong-rh

Timeline (top)

commented ×1labeled ×1mentioned ×1subscribed ×1

Error Message

AssertionError: K must be divisible by blockK

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): 224 On-line CPU(s) list: 0-223 Vendor ID: GenuineIntel Model name: INTEL(R) XEON(R) PLATINUM 8570 CPU family: 6 Model: 207 Thread(s) per core: 2 Core(s) per socket: 56 Socket(s): 2 Stepping: 2 CPU max MHz: 4000.0000 CPU min MHz: 800.0000 BogoMIPS: 4200.00 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 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow 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 user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi 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 ibt 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: 600 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-55,112-167 NUMA node1 CPU(s): 56-111,168-223 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 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

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                : version 4.3.2
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.11.0+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A
XPU 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-6.8.0-85-generic-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 13.0.88
CUDA_MODULE_LOADING set to   :
GPU models and configuration :
GPU 0: NVIDIA B200
GPU 1: NVIDIA B200
GPU 2: NVIDIA B200
GPU 3: NVIDIA B200
GPU 4: NVIDIA B200
GPU 5: NVIDIA B200
GPU 6: NVIDIA B200
GPU 7: NVIDIA B200

Nvidia driver version        : 580.105.08
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):                               224
On-line CPU(s) list:                  0-223
Vendor ID:                            GenuineIntel
Model name:                           INTEL(R) XEON(R) PLATINUM 8570
CPU family:                           6
Model:                                207
Thread(s) per core:                   2
Core(s) per socket:                   56
Socket(s):                            2
Stepping:                             2
CPU max MHz:                          4000.0000
CPU min MHz:                          800.0000
BogoMIPS:                             4200.00
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 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow 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 user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi 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 ibt 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:                             600 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-55,112-167
NUMA node1 CPU(s):                    56-111,168-223
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
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==0.6.8.post1
[pip3] mypy-extensions==1.0.0
[pip3] numpy==2.2.6
[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-cudnn-frontend==1.18.0
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-cufile==1.15.1.6
[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-cutlass-dsl==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu13==2.28.9
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvshmem-cu13==3.4.5
[pip3] nvidia-nvtx==13.0.85
[pip3] open_clip_torch==2.32.0
[pip3] pytorch-lightning==2.5.2
[pip3] pyzmq==27.1.0
[pip3] segmentation_models_pytorch==0.5.0
[pip3] sentence-transformers==5.2.0
[pip3] terratorch==1.2.2
[pip3] torch==2.11.0+cu130
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.11.0+cu130
[pip3] torchgeo==0.7.0
[pip3] torchmetrics==1.7.4
[pip3] torchvision==0.26.0+cu130
[pip3] transformers==5.5.3
[pip3] transformers-stream-generator==0.0.5
[pip3] triton==3.6.0
[pip3] tritonclient==2.64.0
[pip3] vector-quantize-pytorch==1.21.2
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.20.0
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled; XPU: Disabled
GPU Topology:
  	GPU0	GPU1	GPU2	GPU3	GPU4	GPU5	GPU6	GPU7	NIC0	NIC1	NIC2	NIC3	NIC4	NIC5	NIC6	NIC7	NIC8	NIC9	NIC10	NIC11	NIC12	NIC13	NIC14	NIC15	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NV18	NODE	NODE	NODE	NODE	PXB	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	0-55,112-167	0		N/A
GPU1	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NODE	NODE	NODE	NODE	NODE	NODE	NODE	PXB	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	0-55,112-167	0		N/A
GPU2	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	PXB	NODE	SYS	SYS	SYS	SYS	SYS	SYS	0-55,112-167	0		N/A
GPU3	NV18	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	PXB	SYS	SYS	SYS	SYS	SYS	SYS	0-55,112-167	0		N/A
GPU4	NV18	NV18	NV18	NV18	 X 	NV18	NV18	NV18	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PXB	NODE	NODE	NODE	NODE	NODE	56-111,168-223	1		N/A
GPU5	NV18	NV18	NV18	NV18	NV18	 X 	NV18	NV18	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	NODE	NODE	PXB	NODE	NODE	56-111,168-223	1		N/A
GPU6	NV18	NV18	NV18	NV18	NV18	NV18	 X 	NV18	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	PXB	NODE	56-111,168-223	1		N/A
GPU7	NV18	NV18	NV18	NV18	NV18	NV18	NV18	 X 	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	PXB	56-111,168-223	1		N/A
NIC0	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	 X 	PIX	PIX	PIX	NODE	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC1	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	PIX	 X 	PIX	PIX	NODE	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC2	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	PIX	PIX	 X 	PIX	NODE	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC3	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	PIX	PIX	PIX	 X 	NODE	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC4	PXB	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	 X 	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC5	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	 X 	PIX	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC6	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	PIX	 X 	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC7	NODE	PXB	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	NODE	NODE	 X 	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC8	NODE	NODE	PXB	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	 X 	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC9	NODE	NODE	NODE	PXB	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	 X 	SYS	SYS	SYS	SYS	SYS	SYS
NIC10	SYS	SYS	SYS	SYS	PXB	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	NODE	NODE	NODE	NODE	NODE
NIC11	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	 X 	PIX	NODE	NODE	NODE
NIC12	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	PIX	 X 	NODE	NODE	NODE
NIC13	SYS	SYS	SYS	SYS	NODE	PXB	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	NODE	NODE	 X 	NODE	NODE
NIC14	SYS	SYS	SYS	SYS	NODE	NODE	PXB	NODE	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	 X 	NODE
NIC15	SYS	SYS	SYS	SYS	NODE	NODE	NODE	PXB	SYS	SYS	SYS	SYS	SYS	SYS	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
  NIC10: mlx5_10
  NIC11: mlx5_11
  NIC12: mlx5_12
  NIC13: mlx5_13
  NIC14: mlx5_14
  NIC15: mlx5_15

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=void
NVIDIA_REQUIRE_CUDA=cuda>=13.0 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>=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 brand=unknown,driver>=575,driver<576 brand=grid,driver>=575,driver<576 brand=tesla,driver>=575,driver<576 brand=nvidia,driver>=575,driver<576 brand=quadro,driver>=575,driver<576 brand=quadrortx,driver>=575,driver<576 brand=nvidiartx,driver>=575,driver<576 brand=vapps,driver>=575,driver<576 brand=vpc,driver>=575,driver<576 brand=vcs,driver>=575,driver<576 brand=vws,driver>=575,driver<576 brand=cloudgaming,driver>=575,driver<576
NVIDIA_DRIVER_CAPABILITIES=compute,utility
CUDA_VERSION=13.0.2
VLLM_ENABLE_CUDA_COMPATIBILITY=0
LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
CUDA_HOME=/usr/local/cuda
CUDA_HOME=/usr/local/cuda
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

---

AssertionError: K must be divisible by blockK

---

(Worker_TP6 pid=11321) ERROR 04-29 00:05:12 [multiproc_executor.py:870]
    File ".../vllm/model_executor/layers/fused_moe/oracle/unquantized.py", line 315,
      in convert_to_unquantized_kernel_format
    File ".../vllm/model_executor/layers/quantization/utils/flashinfer_utils.py", line 195,
      in convert_moe_weights_to_flashinfer_trtllm_block_layout
      tmp_weights2 = convert_to_block_layout(tmp_weights2.view(torch.uint8), block_k)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    File ".../flashinfer/fused_moe/core.py", line 200, in convert_to_block_layout
      assert K % blockK == 0, "K must be divisible by blockK"
             ^^^^^^^^^^^^^^^
  AssertionError: K must be divisible by blockK

---

# flashinfer/fused_moe/core.py
  def convert_to_block_layout(input_tensor: torch.Tensor, blockK: int) -> torch.Tensor:
      M, K = input_tensor.shape
      assert K % blockK == 0, "K must be divisible by blockK"
      return input_tensor.view(M, K // blockK, blockK).permute(1, 0, 2).contiguous()

---

vllm serve Qwen/Qwen3-30B-A3B --tensor-parallel-size 8

RAW_BUFFERClick to expand / collapse

Your current environment

<details> <summary>The output of <code>python collect_env.py</code></summary>

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                : version 4.3.2
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.11.0+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A
XPU 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-6.8.0-85-generic-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 13.0.88
CUDA_MODULE_LOADING set to   :
GPU models and configuration :
GPU 0: NVIDIA B200
GPU 1: NVIDIA B200
GPU 2: NVIDIA B200
GPU 3: NVIDIA B200
GPU 4: NVIDIA B200
GPU 5: NVIDIA B200
GPU 6: NVIDIA B200
GPU 7: NVIDIA B200

Nvidia driver version        : 580.105.08
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):                               224
On-line CPU(s) list:                  0-223
Vendor ID:                            GenuineIntel
Model name:                           INTEL(R) XEON(R) PLATINUM 8570
CPU family:                           6
Model:                                207
Thread(s) per core:                   2
Core(s) per socket:                   56
Socket(s):                            2
Stepping:                             2
CPU max MHz:                          4000.0000
CPU min MHz:                          800.0000
BogoMIPS:                             4200.00
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 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow 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 user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi 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 ibt 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:                             600 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-55,112-167
NUMA node1 CPU(s):                    56-111,168-223
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
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==0.6.8.post1
[pip3] mypy-extensions==1.0.0
[pip3] numpy==2.2.6
[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-cudnn-frontend==1.18.0
[pip3] nvidia-cufft==12.0.0.61
[pip3] nvidia-cufile==1.15.1.6
[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-cutlass-dsl==4.4.2
[pip3] nvidia-cutlass-dsl-libs-base==4.4.2
[pip3] nvidia-ml-py==13.595.45
[pip3] nvidia-nccl-cu13==2.28.9
[pip3] nvidia-nvjitlink==13.0.88
[pip3] nvidia-nvshmem-cu13==3.4.5
[pip3] nvidia-nvtx==13.0.85
[pip3] open_clip_torch==2.32.0
[pip3] pytorch-lightning==2.5.2
[pip3] pyzmq==27.1.0
[pip3] segmentation_models_pytorch==0.5.0
[pip3] sentence-transformers==5.2.0
[pip3] terratorch==1.2.2
[pip3] torch==2.11.0+cu130
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.11.0+cu130
[pip3] torchgeo==0.7.0
[pip3] torchmetrics==1.7.4
[pip3] torchvision==0.26.0+cu130
[pip3] transformers==5.5.3
[pip3] transformers-stream-generator==0.0.5
[pip3] triton==3.6.0
[pip3] tritonclient==2.64.0
[pip3] vector-quantize-pytorch==1.21.2
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.20.0
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled; XPU: Disabled
GPU Topology:
  	GPU0	GPU1	GPU2	GPU3	GPU4	GPU5	GPU6	GPU7	NIC0	NIC1	NIC2	NIC3	NIC4	NIC5	NIC6	NIC7	NIC8	NIC9	NIC10	NIC11	NIC12	NIC13	NIC14	NIC15	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NV18	NODE	NODE	NODE	NODE	PXB	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	0-55,112-167	0		N/A
GPU1	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NV18	NODE	NODE	NODE	NODE	NODE	NODE	NODE	PXB	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	0-55,112-167	0		N/A
GPU2	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NV18	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	PXB	NODE	SYS	SYS	SYS	SYS	SYS	SYS	0-55,112-167	0		N/A
GPU3	NV18	NV18	NV18	 X 	NV18	NV18	NV18	NV18	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	PXB	SYS	SYS	SYS	SYS	SYS	SYS	0-55,112-167	0		N/A
GPU4	NV18	NV18	NV18	NV18	 X 	NV18	NV18	NV18	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	PXB	NODE	NODE	NODE	NODE	NODE	56-111,168-223	1		N/A
GPU5	NV18	NV18	NV18	NV18	NV18	 X 	NV18	NV18	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	NODE	NODE	PXB	NODE	NODE	56-111,168-223	1		N/A
GPU6	NV18	NV18	NV18	NV18	NV18	NV18	 X 	NV18	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	PXB	NODE	56-111,168-223	1		N/A
GPU7	NV18	NV18	NV18	NV18	NV18	NV18	NV18	 X 	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	PXB	56-111,168-223	1		N/A
NIC0	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	 X 	PIX	PIX	PIX	NODE	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC1	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	PIX	 X 	PIX	PIX	NODE	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC2	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	PIX	PIX	 X 	PIX	NODE	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC3	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	PIX	PIX	PIX	 X 	NODE	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC4	PXB	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	 X 	NODE	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC5	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	 X 	PIX	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC6	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	PIX	 X 	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC7	NODE	PXB	NODE	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	NODE	NODE	 X 	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC8	NODE	NODE	PXB	NODE	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	 X 	NODE	SYS	SYS	SYS	SYS	SYS	SYS
NIC9	NODE	NODE	NODE	PXB	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	NODE	 X 	SYS	SYS	SYS	SYS	SYS	SYS
NIC10	SYS	SYS	SYS	SYS	PXB	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	 X 	NODE	NODE	NODE	NODE	NODE
NIC11	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	 X 	PIX	NODE	NODE	NODE
NIC12	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	PIX	 X 	NODE	NODE	NODE
NIC13	SYS	SYS	SYS	SYS	NODE	PXB	NODE	NODE	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	NODE	NODE	 X 	NODE	NODE
NIC14	SYS	SYS	SYS	SYS	NODE	NODE	PXB	NODE	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	SYS	NODE	NODE	NODE	NODE	 X 	NODE
NIC15	SYS	SYS	SYS	SYS	NODE	NODE	NODE	PXB	SYS	SYS	SYS	SYS	SYS	SYS	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
  NIC10: mlx5_10
  NIC11: mlx5_11
  NIC12: mlx5_12
  NIC13: mlx5_13
  NIC14: mlx5_14
  NIC15: mlx5_15

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=void
NVIDIA_REQUIRE_CUDA=cuda>=13.0 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>=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 brand=unknown,driver>=575,driver<576 brand=grid,driver>=575,driver<576 brand=tesla,driver>=575,driver<576 brand=nvidia,driver>=575,driver<576 brand=quadro,driver>=575,driver<576 brand=quadrortx,driver>=575,driver<576 brand=nvidiartx,driver>=575,driver<576 brand=vapps,driver>=575,driver<576 brand=vpc,driver>=575,driver<576 brand=vcs,driver>=575,driver<576 brand=vws,driver>=575,driver<576 brand=cloudgaming,driver>=575,driver<576
NVIDIA_DRIVER_CAPABILITIES=compute,utility
CUDA_VERSION=13.0.2
VLLM_ENABLE_CUDA_COMPATIBILITY=0
LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
CUDA_HOME=/usr/local/cuda
CUDA_HOME=/usr/local/cuda
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

</details>

🐛 Describe the bug

When loading Qwen/Qwen3-30B-A3B on 8x B200 with TP=8, all 8 TP workers fail at engine init with an AssertionError from flashinfer's convert_to_block_layout:

AssertionError: K must be divisible by blockK

The model's per-expert weight K-dim does not divide the block_k chosen by vLLM's flashinfer trtllm block-layout conversion path. The error fires in the unquantized MoE oracle path — i.e., the model is loaded without an explicit quantization argument and routed through flashinfer_utils.convert_moe_weights_to_flashinfer_trtllm_block_layout.

Stack trace (from one of the 8 workers — identical on all)

(Worker_TP6 pid=11321) ERROR 04-29 00:05:12 [multiproc_executor.py:870]
  File ".../vllm/model_executor/layers/fused_moe/oracle/unquantized.py", line 315,
    in convert_to_unquantized_kernel_format
  File ".../vllm/model_executor/layers/quantization/utils/flashinfer_utils.py", line 195,
    in convert_moe_weights_to_flashinfer_trtllm_block_layout
    tmp_weights2 = convert_to_block_layout(tmp_weights2.view(torch.uint8), block_k)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".../flashinfer/fused_moe/core.py", line 200, in convert_to_block_layout
    assert K % blockK == 0, "K must be divisible by blockK"
           ^^^^^^^^^^^^^^^
AssertionError: K must be divisible by blockK

flashinfer's helper (verbatim):

# flashinfer/fused_moe/core.py
def convert_to_block_layout(input_tensor: torch.Tensor, blockK: int) -> torch.Tensor:
    M, K = input_tensor.shape
    assert K % blockK == 0, "K must be divisible by blockK"
    return input_tensor.view(M, K // blockK, blockK).permute(1, 0, 2).contiguous()

So the precondition belongs to flashinfer; the responsibility for picking a compatible block_k (or padding / routing differently) sits in vLLM at flashinfer_utils.py:195.

Reproduction

vllm serve Qwen/Qwen3-30B-A3B --tensor-parallel-size 8

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 AssertionError occurs because the model's per-expert weight K-dim does not divide the block_k chosen by vLLM's flashinfer trtllm block-layout conversion path, and a compatible block_k should be picked or the model should be padded/routed differently.

Guidance

Investigate the flashinfer_utils.py file at line 195 to understand how block_k is chosen and consider modifying it to ensure compatibility with the model's K-dim.
Check the model's documentation or configuration to see if there are any specific requirements or recommendations for block_k or tensor parallelism.
Consider padding the model's weights to make K divisible by blockK as a temporary workaround.
Review the flashinfer library's documentation to see if there are any known issues or limitations related to block layout conversion.

Example

# Example of how to pad the model's weights to make K divisible by blockK
def pad_weights(weights, blockK):
    K = weights.shape[1]
    padding = blockK - (K % blockK)
    if padding != blockK:
        weights = torch.cat((weights, torch.zeros((weights.shape[0], padding), dtype=weights.dtype)), dim=1)
    return weights

Notes

The provided stack trace and code snippet suggest that the issue is related to the block layout conversion in flashinfer, and the solution will likely involve modifying the flashinfer_utils.py file or the model's configuration.

Recommendation

Apply a workaround by padding the model's weights to make K divisible by blockK, as shown in the example code snippet, until a more permanent solution can be implemented.

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?

#api #training loop #device allocation #model download #environment variable

Still need to ship something?

×6

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

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

vllm - 💡(How to fix) Fix [Bug]: Qwen3-30B-A3B on B200 (TP=8) — K must be divisible by blockK in flashinfer convert_to_block_layout (unquantized MoE oracle path) [1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Fix Action

Fix / Workaround

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

Code Example

Your current environment

🐛 Describe the bug

Stack trace (from one of the 8 workers — identical on all)

Reproduction

Before submitting a new issue...

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

TRENDING

vllm - 💡(How to fix) Fix [Bug]: Qwen3-30B-A3B on B200 (TP=8) — K must be divisible by blockK in flashinfer convert_to_block_layout (unquantized MoE oracle path) [1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Fix Action

Fix / Workaround

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

Code Example

Your current environment

🐛 Describe the bug

Stack trace (from one of the 8 workers — identical on all)

Reproduction

Before submitting a new issue...

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING