AIRust★ 6⑂ 1 forks
avifenesh/memra
MEMRA - AI Accelerator for RTX
Memra is a from‑scratch LLM inference implementation optimized for RTX 5090 (sm_120a) and H100 (sm_90a) architectures in Rust.
// KEY FEATURES
- Support for sm_120a and sm_90a
- Written in pure Rust with no external dependencies
- Efficient GPU memory usage
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram