Registry / ai-ml / sgl-deep-gemm

sgl-deep-gemm

JSON →
library0.1.2pypypiunverified

A SGLang fork of DeepGemm providing optimized GEMM operations for deep learning. Current version 0.1.2, updated June 2024. Release cadence is occasional.

ai-mldevops
pip install sgl-deep-gemm
github ↗homepage ↗
INSTALL
IMPORT
SIG · SGL-DEEP-GEMM
S
sgl-deep-gemm
ai-mlpythonv0.1.2
harness data pending
Install & Compatibility
Where this runs

No compatibility data collected yet for this library.

Code
Verified usage

Verified import paths — ran on the pinned version, not inferred.

jit_gemm
✓ from deep_gemm import jit_gemm
✗ from deep_gemm import jit_gemm

Perform a basic GEMM operation using the JIT kernel.

import torch from deep_gemm import jit_gemm a = torch.randn(128, 128, device='cuda') b = torch.randn(128, 128, device='cuda') c = jit_gemm(a, b) print(c.shape)
Debug
Known issues
gotchaImport as 'deep_gemm' not 'sgl_deep_gemm'.
fix
Use 'from deep_gemm import ...'
affects: all
breakingRequires CUDA-capable GPU and torch compiled with CUDA. No CPU fallback.
fix
Ensure torch.cuda.is_available() before use.
affects: all
Upgrade
Version history
0.1.2latest on PyPI · released Jun 2, 2026
Audit
Dependencies

No dependency data recorded yet.

Agent activity
12 hits · last 30 days
node
10
OpenAI (training)
1
Resources
githubhttps://github.com/sgl-project/DeepGEMM/tree/release ↗
homepagehttps://github.com/sgl-project/DeepGEMM/tree/release ↗
sgl-deep-gemm — pip install sgl-deep-gemm · libregistry