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

[Kernel][Quantization][MoE] add marlin kernel support for turing (sm75) (#29901)

Browse Source 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
Jinzhen Lin
2025-12-17 06:35:28 +08:00
committed by GitHub
parent eaa82a709a
commit ce96857fdd
16 changed files with 729 additions and 513 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
csrc/quantization/gptq_marlin/dequant.h
View File

@@ -67,7 +67,7 @@ where `scale_factor * multiplier` can be computed at weight loading.
namespace MARLIN_NAMESPACE_NAME {
#if !defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 800
#if !defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 750
// Lookup-table based 3-input logical operation; explicitly used for
// dequantization as the compiler does not seem to automatically recognize it in
// all cases.