deepseek-ai/DeepGEMM
DeepGEMM: clean and efficient BLAS kernel library on GPU
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
DeepGEMM is a unified, high-performance tensor core kernel library that brings together the key computation primitives of modern large language models — GEMMs (FP8, FP4, BF16), fused MoE with overlapped communication (Mega MoE), MQA scoring for the lightning indexer, HyperConnection (HC), and more — into a single, cohesive CUDA codebase. All kernels are compiled at runtime through DeepJIT, requiring no CUDA compilation during installation. DeepGEMM leverages some concepts from CUTLASS and CuTe, but avoids heavy reliance on their templates or algebras. The library is designed for simplicity, with only a limited number of core kernel functions, making it a clean and accessible resource for learning NVIDIA GPU kernel optimization techniques. Despite its lightweight design, DeepGEMM's performance matches or exceeds expert-tuned libraries across various matrix shapes. Then, import deepgemm in your Python project, and enjoy! This library provides optimized GEMM kernels for NVIDIA GPUs with a naming convention: D = C…
Read the full README ↗ · Preview checked 2026-11-17T18:52:59.760Z
Inside the original README — Document outline
- DeepGEMM
- News
- Quick start
- Requirements
- Development
- Installation
- Interfaces
- Notices
- Normal dense GEMMs (non-grouped)
- Grouped GEMMs (contiguous layout)
- Grouped GEMMs (masked layout)
- V3.2 MQA kernels for the indexer
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
DeepGEMM: clean and efficient BLAS kernel library on GPU
Repository facts
- Owner
- deepseek-ai
- Primary language
- Cuda
- Stars
- 8,534
- Forks
- 1,361
- Open issues + pull requests
- 150
- License
- MIT
- Archived
- No
- Default branch
- main
- Created
- 2025-02-13T09:09:21.000Z
- Last push
- 2026-09-30T01:48:05.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-06T12:03:57.824Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.