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 0.1.7
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-0.1.7-py3-none-manylinux2014_x86_64.whl | Python 3 | none | Linux glibc 2.17+ x86-64 | Details |
| sgl_deep_gemm-0.1.7-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-0.1.7-py3-none-manylinux2014_x86_64.whl
| Download URL | sgl_deep_gemm-0.1.7-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 |
f4e67086dc685ddcfcbb7833cc9770afd850cab23e173e77b9b18c19de0c2836
|
|
BLAKE2b-256 checksum How to use checksums |
7aad6f9aa43796dc2f028cbe62b43c276dbce8091b955eb918d42a147d97b377
|
| 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-0.1.7-py3-none-manylinux2014_aarch64.whl
| Download URL | sgl_deep_gemm-0.1.7-py3-none-manylinux2014_aarch64.whl |
|---|---|
| Size | 4.7 MB |
| Tags | Linux glibc 2.17+ ARM64 Python 3 |
|
SHA-256 checksum How to use checksums |
9549a3d1c2028ca5b71c1ad91a66c74a1ef2a93ec014a8d1378ce157a8bb1d30
|
|
BLAKE2b-256 checksum How to use checksums |
e281204823503054b3cee5bc8070dd5011cc7df2ce9af53d6c765b967b59efa9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
