minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Kernel] Introduce sglang.kernels namespace and migrate scattered triton_ops kernels (RFC #29630, Phase 2) (#30044)

Browse Source 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Xiaoyu Zhang
2026-07-10 21:41:08 +08:00
committed by GitHub
co-authored by Claude Opus 4.8
parent e9493a015c
commit 6ed9843b57
161 changed files with 3329 additions and 459 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/bench_attention_sink/bench_attention_sink_triton.py
+2 -2
View File
@@ -3,10 +3,10 @@ import argparse
import torch
import triton
from sglang.srt.layers.attention.triton_ops.decode_attention import (
from sglang.kernels.ops.attention.decode_attention import (
decode_attention_fwd_grouped,
)
from sglang.srt.layers.attention.triton_ops.extend_attention import extend_attention_fwd
from sglang.kernels.ops.attention.extend_attention import extend_attention_fwd
# gpt oss
head_num = 64