deepseek-ai / deepseek-ai/DeepEP
assert not compatible on Blackwell GPUs
- Dominant language
- Cuda
- Stars
- 10.1k
- Forks
- 1.4k
- Avg merge
- 4d 1h
- Merged PRs (30d)
- 2
Description
File "/usr/local/lib/python3.12/dist-packages/nvidia_cutlass_dsl/python_packages/cutlass/cutlass_dsl/cuda_jit_executor.py", line 126, in num_devices
raise DSLCudaRuntimeError(dev_err, cuda_runtime.cudaGetErrorName(dev_err))
cutlass.base_dsl.common.DSLCudaRuntimeError: DSLCudaRuntimeError: (, b'cudaErrorInsufficientDriver') (error code: 35)
Error Code: 35
🔍 Additional Context:
- Error name: (, b'cudaErrorInsufficientDriver')
- Error code: 35
- CUDA_TOOLKIT_PATH: not set
- Target SM ARCH: not set
📊 GPU Information:
- CUDA devices available: 8 (current: )
- Architecture: Blackwell (sm_100a)
- Compatible SM archs: sm_100a
- Total Memory: 178.36 GB
Compatibility Check:
❌ Error: Target SM ARCH unknown is not compatible
💡 Please use one of SM ARCHs: sm_100a
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.