vllm - 💡(How to fix) Fix [Bug]: CUBLAS_STATUS_INVALID_VALUE on Qwen3.5-122B-A10B-FP8 during profile run [1 comments, 2 participants]

vllm2026-03-11 11:38:50

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#36783•Fetched 2026-04-08 00:34:43

View on GitHub

Comments

Participants

Timeline

Reactions

Author

twright8

Participants

haosdent

twright8

Timeline (top)

subscribed ×2commented ×1labeled ×1unsubscribed ×1

Error Message

RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling cublasGemmEx( handle, opa, opb, m, n, k, &falpha, a, CUDA_R_16BF, lda, b, CUDA_R_16BF, ldb, &fbeta, c, std::is_same_v<C_Dtype, float> ? CUDA_R_32F : CUDA_R_16BF, ldc, compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP)

Code Example

==============================
        System Info
==============================
OS                           : Ubuntu 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 11.4.0-1ubuntu1~22.04) 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+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.1 (main, Jan  8 2024, 04:46:10) [Clang 17.0.6 ] (64-bit runtime)
Python platform              : Linux-4.4.0-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 13.0.48
CUDA_MODULE_LOADING set to   :
GPU models and configuration : GPU 0: NVIDIA B200
Nvidia driver version        : 580.95.05
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, 48 bits virtual
Byte Order:          Little Endian
CPU(s):              17
On-line CPU(s) list: 0-16
Vendor ID:           GenuineIntel
Model name:          unknown
CPU family:          6
Model:               207
Thread(s) per core:  1
Core(s) per socket:  17
Socket(s):           1
Stepping:            unknown
BogoMIPS:            2100.00
Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm avx512f avx512dq rdseed adx smap clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512vbmi umip avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk amx_bf16 avx512_fp16 amx_tile amx_int8 arch_capabilities
Hypervisor vendor:   KVM
Virtualization type: full

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.4
[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==9.15.1.9
[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==4.4.1
[pip3] nvidia-cutlass-dsl-libs-base==4.4.1
[pip3] nvidia-ml-py==13.590.48
[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] pyzmq==27.1.0
[pip3] torch==2.10.0+cu130
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0+cu130
[pip3] torchvision==0.25.0+cu130
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.17.1
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0 CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X                              N/A

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

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=GPU-c37141d3-35f4-86d8-de23-8da41195cb13
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
NCCL_VERSION=2.27.7-1
NVIDIA_DRIVER_CAPABILITIES=all
NVIDIA_PRODUCT_NAME=CUDA
CUDA_VERSION=13.0.0
LD_LIBRARY_PATH=/usr/local/lib/python3.12/site-packages/cv2/../../lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
OMP_NUM_THREADS=1
CUDA_HOME=/usr/local/cuda
CUDA_HOME=/usr/local/cuda
MKL_NUM_THREADS=1
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

---

RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasGemmEx( handle, opa, opb, m, n, k, &falpha, a, CUDA_R_16BF, lda, b, CUDA_R_16BF, ldb, &fbeta, c, std::is_same_v<C_Dtype, float> ? CUDA_R_32F : CUDA_R_16BF, ldc, compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP)`

---

from vllm import LLM

llm = LLM(
    model="Qwen/Qwen3.5-122B-A10B-FP8",
    tensor_parallel_size=1,
    gpu_memory_utilization=0.95,
    max_model_len=2048,
    enable_prefix_caching=True,
    trust_remote_code=True,
    language_model_only=True,
    reasoning_parser="qwen3",
    enforce_eager=True,
)

---

INFO  [gpu_model_runner.py:4364] Model loading took 115.37 GiB memory and 65.025039 seconds
...
ERROR [core.py:1100] EngineCore failed to start.
File "/usr/local/lib/python3.12/site-packages/vllm/model_executor/models/qwen3_5.py", line 738, in forward
    hidden_states = self.language_model.model(
File "/usr/local/lib/python3.12/site-packages/vllm/model_executor/models/qwen3_next.py", line 1132, in forward
...
File "/tmp/torchinductor_root/.../czrdh5y437l2gidf2aq5iszgsyvitdzzhssngyetwkopcwpvsbrr.py", line 672, in call
    extern_kernels.mm(buf2, reinterpret_tensor(arg7_1, (3072, 128), (1, 3072), 0), out=buf11)
RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasGemmEx(...)`

RAW_BUFFERClick to expand / collapse

Your current environment

<details> <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) 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+cu130
Is debug build               : False
CUDA used to build PyTorch   : 13.0
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.1 (main, Jan  8 2024, 04:46:10) [Clang 17.0.6 ] (64-bit runtime)
Python platform              : Linux-4.4.0-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 13.0.48
CUDA_MODULE_LOADING set to   :
GPU models and configuration : GPU 0: NVIDIA B200
Nvidia driver version        : 580.95.05
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, 48 bits virtual
Byte Order:          Little Endian
CPU(s):              17
On-line CPU(s) list: 0-16
Vendor ID:           GenuineIntel
Model name:          unknown
CPU family:          6
Model:               207
Thread(s) per core:  1
Core(s) per socket:  17
Socket(s):           1
Stepping:            unknown
BogoMIPS:            2100.00
Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm avx512f avx512dq rdseed adx smap clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512vbmi umip avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk amx_bf16 avx512_fp16 amx_tile amx_int8 arch_capabilities
Hypervisor vendor:   KVM
Virtualization type: full

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.4
[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==9.15.1.9
[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==4.4.1
[pip3] nvidia-cutlass-dsl-libs-base==4.4.1
[pip3] nvidia-ml-py==13.590.48
[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] pyzmq==27.1.0
[pip3] torch==2.10.0+cu130
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0+cu130
[pip3] torchvision==0.25.0+cu130
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.17.1
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0 CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X                              N/A

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

==============================
     Environment Variables
==============================
NVIDIA_VISIBLE_DEVICES=GPU-c37141d3-35f4-86d8-de23-8da41195cb13
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
NCCL_VERSION=2.27.7-1
NVIDIA_DRIVER_CAPABILITIES=all
NVIDIA_PRODUCT_NAME=CUDA
CUDA_VERSION=13.0.0
LD_LIBRARY_PATH=/usr/local/lib/python3.12/site-packages/cv2/../../lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
OMP_NUM_THREADS=1
CUDA_HOME=/usr/local/cuda
CUDA_HOME=/usr/local/cuda
MKL_NUM_THREADS=1
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

</details>

🐛 Describe the bug

vllm==0.17.1

Loading Qwen3.5-122B-A10B-FP8 on a single B200 fails with a CUBLAS_STATUS_INVALID_VALUE error during the profiling/dummy run phase (_dummy_run → determine_available_memory). The model weights load successfully (115.37 GiB, ~65s), but the engine crashes immediately after during KV cache initialization.

The error occurs inside inductor-generated code at a cublasGemmEx call in the first decoder layer's linear attention projection:

RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasGemmEx( handle, opa, opb, m, n, k, &falpha, a, CUDA_R_16BF, lda, b, CUDA_R_16BF, ldb, &fbeta, c, std::is_same_v<C_Dtype, float> ? CUDA_R_32F : CUDA_R_16BF, ldc, compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP)`

The stack trace points to qwen3_5.py → qwen3_next.py → inductor-compiled forward → extern_kernels.mm with a reinterpret_tensor of shape (3072, 128).

Memory is not the issue — the B200 has 192GB and the model only uses ~115GB.

How to reproduce

from vllm import LLM

llm = LLM(
    model="Qwen/Qwen3.5-122B-A10B-FP8",
    tensor_parallel_size=1,
    gpu_memory_utilization=0.95,
    max_model_len=2048,
    enable_prefix_caching=True,
    trust_remote_code=True,
    language_model_only=True,
    reasoning_parser="qwen3",
    enforce_eager=True,
)

Run on a B200 GPU. Crashes during engine initialization before any inference begins.

Relevant log output

INFO  [gpu_model_runner.py:4364] Model loading took 115.37 GiB memory and 65.025039 seconds
...
ERROR [core.py:1100] EngineCore failed to start.
File "/usr/local/lib/python3.12/site-packages/vllm/model_executor/models/qwen3_5.py", line 738, in forward
    hidden_states = self.language_model.model(
File "/usr/local/lib/python3.12/site-packages/vllm/model_executor/models/qwen3_next.py", line 1132, in forward
...
File "/tmp/torchinductor_root/.../czrdh5y437l2gidf2aq5iszgsyvitdzzhssngyetwkopcwpvsbrr.py", line 672, in call
    extern_kernels.mm(buf2, reinterpret_tensor(arg7_1, (3072, 128), (1, 3072), 0), out=buf11)
RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasGemmEx(...)`

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

To resolve the CUBLAS_STATUS_INVALID_VALUE error, we need to adjust the CUDA and cuBLAS configuration.

Update CUDA and cuBLAS versions: Ensure that the CUDA and cuBLAS versions are compatible with the PyTorch version (2.10.0+cu130) and the NVIDIA driver version (580.95.05).
Check cuBLAS settings: Verify that the cuBLAS settings are correctly configured for the specific GPU architecture (NVIDIA B200).
Modify the cublasGemmEx call: Update the cublasGemmEx call in the inductor-generated code to use the correct data types and tensor shapes.

Example code modifications:

import torch

# Update CUDA and cuBLAS versions
torch.cuda.set_device(0)
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True

# Modify the cublasGemmEx call
def modified_cublas_gemm_ex(handle, opa, opb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc, compute_type):
    # Update data types and tensor shapes
    a = a.to(torch.float16)
    b = b.to(torch.float16)
    c = c.to(torch.float16)
    # Call cublasGemmEx with updated parameters
    torch.cuda.cublas.cublasGemmEx(handle, opa, opb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc, compute_type)

# Replace the original cublasGemmEx call with the modified version
# in the inductor-generated code

Verification

To verify that the fix worked, run the model with the modified cublasGemmEx call and check for any errors. If the model runs without errors, the fix is successful.

Extra Tips

Ensure that the GPU has sufficient memory to run the model.
Verify that the PyTorch, CUDA, and cuBLAS versions are compatible.
Check the NVIDIA driver version and update it if necessary.
Use the torch.cuda.cublas module to access cuBLAS functions and modify the cublasGemmEx call accordingly.

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 #ssr #installation #latency issue #model loading #dependency error #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]: CUBLAS_STATUS_INVALID_VALUE on Qwen3.5-122B-A10B-FP8 during profile run [1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Code Example

Your current environment

🐛 Describe the bug

How to reproduce

Relevant log output

Before submitting a new issue...

extent analysis

Fix Plan

Verification

Extra Tips

Still need to ship something?

TRENDING

vllm - 💡(How to fix) Fix [Bug]: CUBLAS_STATUS_INVALID_VALUE on Qwen3.5-122B-A10B-FP8 during profile run [1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Code Example

Your current environment

🐛 Describe the bug

How to reproduce

Relevant log output

Before submitting a new issue...

extent analysis

Fix Plan

Verification

Extra Tips

Still need to ship something?

RELATED_DISCOVERY

TRENDING