minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

feat(sgl-kernel): add InfLLM v2 attention kernels (#29383)

Browse Source 
Co-authored-by: Size Wang <paulgeorge13hhhhh@gmail.com>
Co-authored-by: lijiayi <lijiayi@modelbest.cn>
Co-authored-by: suhmily10 <suhmily@gmail.com>
Co-authored-by: Xiaoyue Xu <xiaoyue.xu.me@gmail.com>
Co-authored-by: hansjohn <74091612+hansjohn@users.noreply.github.com>
Co-authored-by: zhangyan <1762895426@qq.com>
This commit is contained in:
cauphe
2026-07-06 22:46:54 -07:00
committed by GitHub
co-authored by Size Wang lijiayi suhmily10 Xiaoyue Xu hansjohn zhangyan
parent be70bfbdbb
commit 9bd02dc5b9
33 changed files with 6026 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
sgl-kernel/python/sgl_kernel/infllm_v2/__init__.py
+7
View File
@@ -0,0 +1,7 @@
from sgl_kernel.infllm_v2.attention import infllmv2_attn_stage1
from sgl_kernel.infllm_v2.max_pooling import max_pooling_1d_varlen
__all__ = [
"infllmv2_attn_stage1",
"max_pooling_1d_varlen",
]