EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

support cmake for sgl-kernel (#4706)

Browse Source 
Co-authored-by: hebiao064 <hebiaobuaa@gmail.com>
Co-authored-by: yinfan98 <1106310035@qq.com>
This commit is contained in:
Yineng Zhang
2025-03-27 01:42:28 -07:00
committed by GitHub
parent 1b9175cb23
commit 8bf6d7f406
18 changed files with 426 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
sgl-kernel/csrc/attention/lightning_attention_decode_kernel.cu
View File

@@ -18,7 +18,7 @@ limitations under the License.
#include <c10/cuda/CUDAGuard.h>
#include <cuda_fp16.h>
#include <cuda_runtime.h>
#include <torch/extension.h>
#include <torch/all.h>
#define THREADS_PER_BLOCK 128