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/kernels/lora_csgmv/tune_lora_csgmv.py
+6 -6
View File
@@ -58,9 +58,9 @@ from typing import Any, Dict, List, Optional
import torch
import triton
from sglang.srt.lora.triton_ops.chunked_sgmv_expand import _chunked_lora_expand_kernel
from sglang.srt.lora.triton_ops.chunked_sgmv_shrink import _chunked_lora_shrink_kernel
from sglang.srt.lora.triton_ops.lora_tuning_config import (
from sglang.kernels.ops.gemm.chunked_sgmv_expand import _chunked_lora_expand_kernel
from sglang.kernels.ops.gemm.chunked_sgmv_shrink import _chunked_lora_shrink_kernel
from sglang.kernels.ops.gemm.lora_tuning_config import (
DEFAULT_EXPAND_CONFIG,
DEFAULT_SHRINK_CONFIG,
get_lora_config_file_name,
@@ -362,9 +362,9 @@ def save_config(
"..",
"python",
"sglang",
"srt",
"lora",
"triton_ops",
"kernels",
"ops",
"gemm",
"csgmv_configs",
version_dir,
)