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

[2/n] Migrate per_token_group_quant to torch stable ABI (#36058)

Browse Source 
Signed-off-by: Mikayla Gawarecki <mikaylagawarecki@gmail.com>
This commit is contained in:
mikaylagawarecki
2026-03-25 13:15:13 -04:00
committed by GitHub
parent 1ac2ef2e53
commit bf4cc9ed2d
22 changed files with 207 additions and 133 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
csrc/cache_kernels.cu
View File

@@ -7,7 +7,8 @@
#include "cuda_utils.h"
#include "cuda_compat.h"
#include "dispatch_utils.h"
#include "quantization/vectorization_utils.cuh"
#include "libtorch_stable/quantization/vectorization_utils.cuh"
#include "concat_mla_q.cuh"
#ifdef USE_ROCM