avifenesh/memra
Rust + CUDA inference engine for NVIDIA RTX PRO 6000 Blackwell and RTX 5090. Serves safetensors and GGUF over an OpenAI-compatible API, with per-device tuned defaults and speculative decode gated byte-identical to plain decode. Hosted instance: inference.tiyuvta.ai
328
Stars
38
Forks
54.7
Radar Score
Rising
Momentum
Scoring Breakdown
Impact55.4
Velocity51.3
Health58.3
Growth Metrics
7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
OpenEdge ABL
Why it ranks
Strong momentum — adoption is accelerating week over week.
Top 32% globally