wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-08-04 13:24:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Kernel]: Cutlass 2:4 Sparsity + FP8/Int8 Quant Support (#10995)

Browse Source 
Co-authored-by: Faraz Shahsavan <faraz.shahsavan@gmail.com>
Co-authored-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Rahul Tuli <rahul@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
This commit is contained in:
Dipika Sikka
2024-12-18 09:57:16 -05:00
committed by GitHub
co-authored by Faraz Shahsavan ilmarkov Rahul Tuli rshaw@neuralmagic.com <rshaw@neuralmagic.com>
parent f04e407e6b
commit 60508ffda9
30 changed files with 2365 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files
csrc/cutlass_extensions/common.cpp
+11
View File
@@ -0,0 +1,11 @@
#include "cutlass_extensions/common.hpp"
int32_t get_sm_version_num() {
int32_t major_capability, minor_capability;
cudaDeviceGetAttribute(&major_capability, cudaDevAttrComputeCapabilityMajor,
0);
cudaDeviceGetAttribute(&minor_capability, cudaDevAttrComputeCapabilityMinor,
0);
int32_t version_num = major_capability * 10 + minor_capability;
return version_num;
}