xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 23:06:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build] Fix pre-commit errors from #13571 (#13709)

Browse Source 
Signed-off-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
Roger Wang 2025-02-22 16:50:38 -08:00 committed by GitHub
parent 78ac0f591d
commit 82e0d601fc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
csrc/quantization/fp4/nvfp4_scaled_mm_entry.cu
View File

@ -31,7 +31,8 @@ void cutlass_scaled_fp4_mm(torch::Tensor& D, torch::Tensor const& A,
#if defined ENABLE_NVFP4 && ENABLE_NVFP4
return cutlass_scaled_fp4_mm_sm100a(D, A, B, A_sf, B_sf, alpha);
#endif
TORCH_CHECK_NOT_IMPLEMENTED(false, "No compiled nvfp4 mm kernel, vLLM should "
"be compiled using CUDA 12.8 and target "
"compute capability 100 or above.");
TORCH_CHECK_NOT_IMPLEMENTED(false,
"No compiled nvfp4 mm kernel, vLLM should "
"be compiled using CUDA 12.8 and target "
"compute capability 100 or above.");
}

5
csrc/quantization/fp4/nvfp4_scaled_mm_kernels.cu
View File

@ -194,8 +194,9 @@ void runGemm(at::Tensor& D, at::Tensor const& A, at::Tensor const& B,
at::Tensor const& A_sf, at::Tensor const& B_sf,
at::Tensor const& alpha, int64_t m, int64_t n, int64_t k,
cudaStream_t stream) {
TORCH_CHECK(false, "Unsupported CUTLASS version. Set VLLM_CUTLASS_SRC_DIR to "
"a CUTLASS 3.8 source directory to enable support.");
TORCH_CHECK(false,
"Unsupported CUTLASS version. Set VLLM_CUTLASS_SRC_DIR to "
"a CUTLASS 3.8 source directory to enable support.");
}
#endif // defined(CUTLASS_ARCH_MMA_SM100_SUPPORTED)