Files

Lianmin Zheng ac2387279e Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988 )

Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: dhou-xai <dhou@x.ai>
Co-authored-by: Hanming Lu <hanming_lu@berkeley.edu>

2025-03-03 00:12:04 -08:00

3rdparty

Update cutlass dependency (#3966 )

2025-02-28 16:16:31 -08:00

benchmark

use warp shuffle style reduce and flashinfer vectorize (#3628 )

2025-02-19 20:53:51 +08:00

src/sgl-kernel

Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988 )

2025-03-03 00:12:04 -08:00

tests

Revert "[MOE] enable efficient moe_alignment multi-blocks execution (3x~6x)" (#3982 )

2025-02-28 23:57:17 -08:00

.clang-format

format: add clang-format for sgl-kernel (#2483 )

2024-12-14 22:36:04 +08:00

build.sh

use self-hosted to build sgl-kernel (#3154 )

2025-01-26 23:02:57 +08:00

developer_guide.md

support version in sgl-kernel (#3439 )

2025-02-10 03:49:52 +08:00

LICENSE

feat: support sgl-kernel pypi (#2302 )

2024-12-01 20:11:21 +08:00

Makefile

chore: bump sgl-kernel v0.0.3.post3 (#3440 )

2025-02-10 04:00:52 +08:00

pyproject.toml

Revert "[MOE] enable efficient moe_alignment multi-blocks execution (3x~6x)" (#3982 )

2025-02-28 23:57:17 -08:00

README.md

update installation doc for sgl-kernel (#3129 )

2025-01-26 00:00:13 +08:00

setup_rocm.py

Enable custom AR for AMD GPUs and maintain it in sgl-kernel (#3406 )

2025-03-02 15:19:06 -08:00

setup.py

[Feature] Apply Cublas Grouped Gemm kernel (#3629 )

2025-02-18 15:18:31 +08:00

THIRDPARTYNOTICES.txt

add tensorrt_llm common and cutlass_extensions as 3rdparty (#3216 )

2025-01-30 23:04:41 +08:00

README.md

SGL Kernel

Kernel Library for SGLang

Installation

For CUDA 11.8:

pip3 install sgl-kernel -i https://docs.sglang.ai/whl/cu118

For CUDA 12.1 or CUDA 12.4:

pip3 install sgl-kernel