memra
Rust + CUDA LLM inference engine for Blackwell (Tuned specifically on RTX PRO 6000, RTX 5090, B200): OpenAI-compatible (+converse and ant) serving, per-model X hardware exactness gates. NVFP4/mixed (fp8 hybrid, 4o6, etc - correctness, performance, hardware specific adapted) main quant support.
avifenesh/memra
View on GitHub ↗Rust + CUDA LLM inference engine for Blackwell (Tuned specifically on RTX PRO 6000, RTX 5090, B200): OpenAI-compatible (+converse and ant) serving, per-model X hardware exactness gates. NVFP4/mixed (fp8 hybrid, 4o6, etc - correctness, performance, hardware specific adapted) main quant support.
memra grew +100.0% in the last 30 days, ranks 491st of 494 in Local Runtime / Inference Engine, last commit 18 days ago.
Star trajectory
84 days tracked+100.0% in 30d, above the Local Runtime / Inference Engine median of +1.7%.
Last commit 18 days ago, staler than the median of 5d.
How it compares in Local Runtime / Inference Engine
Ranked 491st of 494 by stars.
- Language
- OpenEdge ABL
- License
- Other
- Contributors
- 5
- Forks
- 1
- Watchers
- 1
- Open issues
- 67
- Releases
- 17
- Created
- 2026-07-05
- Stars this week
- +2
You've seen where memra stands today.
Get the moves before everyone else: the 5 Local Runtime / Inference Engine repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.