deepseek-ai/DeepGEMM
GPU tensor core kernel library
DeepGEMM is a high-performance CUDA library providing optimized BLAS kernels and fused operations for large language model inference. It supports various data types and features like fused MoE and runtime compilation to accelerate AI workloads on GPUs.
- GitHub trending history
- 1 day between Jun 19, when Trend began recording, and Nov 4, 2026 · first on Oct 6 · best daily rank #9 (Oct 6)
- Language
- Cuda
- Stars
- 9,156
- Stars gained in 7 days
- +31
- Contributors
- 45
- Forks
- 1,510
- Latest release
- v2.1.1.post3 · October 15, 2025
- Commits
- 199
- Last commit
- October 20, 2026
- Open issues
- 75
- Open pull requests
- 94
README badge
The badge above shows the highest this repository has ranked on GitHub's daily trending since June 19, 2026, and the day it did. Paste the Markdown below into your README. The badge opens this page, and it updates by itself when the repository climbs higher.
[](https://trend.ondo.sh/github/r/deepseek-ai--DeepGEMM/en.html)