biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Build/CI] Fix CUDA 11.8 build (#17679)

Browse Source 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
This commit is contained in:
Tyler Michael Smith
2025-05-22 15:13:54 -04:00
committed by GitHub
parent f8d2cc5f55
commit 6e588da0f4
9 changed files with 78 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
csrc/quantization/cutlass_w8a8/scaled_mm_entry.cu
View File

@@ -123,7 +123,7 @@ bool cutlass_scaled_mm_supports_block_fp8(int64_t cuda_device_capability) {
}
bool cutlass_group_gemm_supported(int64_t cuda_device_capability) {
// CUTLASS groped FP8 kernels need at least CUDA 12.3
// CUTLASS grouped FP8 kernels need at least CUDA 12.3
// and SM90 (Hopper)
#if defined CUDA_VERSION