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

[Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin (#7701)

Browse Source 
Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Lucas Wilkinson
2024-09-23 13:46:26 -04:00
committed by GitHub
parent ee5f34b1c2
commit 86e9c8df29
27 changed files with 1005 additions and 246 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
csrc/quantization/machete/machete_mm_kernel.cuh
View File

@@ -152,7 +152,8 @@ struct MacheteKernelTemplate {
int M = size<0>(layout_A), N = size<1>(layout_D), K = size<1>(layout_A);
int const group_size = maybe_group_size.value_or(K);
int const group_size =
maybe_group_size == -1 ? K : maybe_group_size.value_or(K);
int const scale_k = (K + group_size - 1) / group_size;
TORCH_CHECK(size<0>(layout_A) == M && size<1>(layout_A) == K);