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:
- ABI support: with the help of tvm-ffi wrappers, a single wheel can run on different python versions.
- pypi support: easy installation with
pip install sgl-deep-gemm. No need to manually search for wheel links. - 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
Release files for sgl-deep-gemm 0.1.8rc0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| sgl_deep_gemm-0.1.8rc0-py3-none-manylinux2014_x86_64.whl | Python 3 | none | Linux glibc 2.17+ x86-64 | Details |
| sgl_deep_gemm-0.1.8rc0-py3-none-manylinux2014_aarch64.whl | Python 3 | none | Linux glibc 2.17+ ARM64 | Details |
Total release size: 9.6 MB
Release files / sgl_deep_gemm-0.1.8rc0-py3-none-manylinux2014_x86_64.whl
| Download URL | sgl_deep_gemm-0.1.8rc0-py3-none-manylinux2014_x86_64.whl |
|---|---|
| Size | 4.9 MB |
| Tags | Linux glibc 2.17+ x86-64 Python 3 |
|
SHA-256 checksum How to use checksums |
2f5208f234be21efbc44d958c789e65a0107af51e31a7a8ce2d6d0b67330b88f
|
|
BLAKE2b-256 checksum How to use checksums |
3990934c344b91a28413e4b884f827286afe8026f2d50d512be1e808e8950339
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
Release files / sgl_deep_gemm-0.1.8rc0-py3-none-manylinux2014_aarch64.whl
| Download URL | sgl_deep_gemm-0.1.8rc0-py3-none-manylinux2014_aarch64.whl |
|---|---|
| Size | 4.7 MB |
| Tags | Linux glibc 2.17+ ARM64 Python 3 |
|
SHA-256 checksum How to use checksums |
3c91aab6a0a3022dbf006f00ca951b100d56d086db998fe219ab17c5a0bc81b9
|
|
BLAKE2b-256 checksum How to use checksums |
a264daedc14fdaa0e7870f397efcd45a41e932593f3599f2157bdb447e215fbe
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
