Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

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

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.

File details

Details for the file sgl_deep_gemm-0.1.5rc3-py3-none-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for sgl_deep_gemm-0.1.5rc3-py3-none-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 408b24a41101363110d06fb76f9b4b28a1e9179c8a999d6a577430da881fb5f6
MD5 a87c71fd1f3bd14b45099335bedcf5e0
BLAKE2b-256 ce127caa58fe43e3598a1d986f58c0d655ae86a75d5f43215a68e0e3665b4b1c

See more details on using hashes here.

File details

Details for the file sgl_deep_gemm-0.1.5rc3-py3-none-manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for sgl_deep_gemm-0.1.5rc3-py3-none-manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 38f295cb630af94e7afcfc471edcbcf62c023e0b3c6bb601f22132beb006f7c9
MD5 f72ec3c9981cc4a41fd5921d519d3136
BLAKE2b-256 93ce4bbdc75ee14c2a820595563485f7cc5de58a3d3f77fd93f3e6d1293b9366

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