Introduction

sgl-deep-gemm is a pypi package built from SGLang's customized branch of DeepGemm. Comparing with origina DeepGemm, it supports the following features to better support SGLang:

  1. ABI support: with the help of tvm-ffi wrappers, a single wheel can run on different python versions.
  2. pypi support: easy installation with pip install sgl-deep-gemm. No need to manually search for wheel links.
  3. Fast iteration: add custom kernels and bump versions at no time.

Usage

To build it locally, run bash build_sgl_deep_gemm.sh, then pip install the wheel generated under dist.

To release a new set of wheels, please contact SGLang team and run the release workflow under SGLang repo

For each major version release (0.X.Y -> 0.(X+1).0), a new branch should be created (release/v0.(X+1).0) for stability purpose.

For any incoming pull requests, it should be rebased upon dev branch. Any newly added or modified tests should be put under sgl_deep_gemm/tests

Project links

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.1.5.post2)

2 maintainers

PyPI data
Data sourced directly from PyPI's database.
Avatar for BBuf from gravatar.com BBuf Avatar for zbz123 from gravatar.com zbz123

Credits

Author: SGLang Kernel Team

License expression

Apache-2.0
View SPDX License List

Requires

Python >=3.10

Provides Extra

dev

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

sgl_deep_gemm-0.1.5.post1-py3-none-manylinux2014_x86_64.whl (4.8 MB view details)

Uploaded Python 3

sgl_deep_gemm-0.1.5.post1-py3-none-manylinux2014_aarch64.whl (4.7 MB view details)

Uploaded Python 3

File details

Details for the file sgl_deep_gemm-0.1.5.post1-py3-none-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for sgl_deep_gemm-0.1.5.post1-py3-none-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 1ee11f78218082fcdf6779c1bf4e45eaa7d667fb099db96e29b716be701ea493
MD5 b14ccea1af66007e29bc773201fd564a
BLAKE2b-256 e3c43ef49dafd3bda25002688341a6952301d4b4e71fb6c3cd7297a8dd6faad0

See more details on using hashes here.

File details

Details for the file sgl_deep_gemm-0.1.5.post1-py3-none-manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for sgl_deep_gemm-0.1.5.post1-py3-none-manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 6c556ce3c63c1b96b1d669d76a0167cadf1eb565735a4874cc4d65a0c265bd4c
MD5 9a25f38bc5fd161fd1ac905712bac32c
BLAKE2b-256 61a27c1d50a2848b17d446f83f53812c01d5a999ab3a23a3729a9938dd1a1015

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page