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

Move cached kernel to srt.utils (#10776)

Browse Source
This commit is contained in:
Lifu Huang
2025-09-22 23:00:36 -07:00
committed by GitHub
parent 063c3791fe
commit 9241f4fd20
4 changed files with 120 additions and 122 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/sglang/srt/lora/triton_ops/chunked_sgmv_expand.py
View File

@@ -5,7 +5,7 @@ import triton
import triton.language as tl
from sglang.srt.lora.utils import LoRABatchInfo
from sglang.utils import cached_triton_kernel
from sglang.srt.utils import cached_triton_kernel
@cached_triton_kernel(lambda _, kwargs: (kwargs["NUM_SLICES"], kwargs["BLOCK_M"]))

2
python/sglang/srt/lora/triton_ops/chunked_sgmv_shrink.py
View File

@@ -3,7 +3,7 @@ import triton
import triton.language as tl
from sglang.srt.lora.utils import LoRABatchInfo
from sglang.utils import cached_triton_kernel
from sglang.srt.utils import cached_triton_kernel
@cached_triton_kernel(lambda _, kwargs: (kwargs["NUM_SLICES"], kwargs["BLOCK_M"]))