bw24
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
avifenesh/bw24
View on GitHub ↗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
bw24 grew +12.7% in the last 30 days, ranks 272nd of 494 in Local Runtime / Inference Engine, actively maintained, last commit today.
Star trajectory
54 days tracked+12.7% in 30d, above the Local Runtime / Inference Engine median of +1.7%.
Last commit today, fresher than the median of 5d.
How it compares in Local Runtime / Inference Engine
Ranked 272nd of 494 by stars.
- Language
- OpenEdge ABL
- License
- MIT License
- Contributors
- 8
- Forks
- 38
- Watchers
- 25
- Open issues
- 4
- Releases
- 132
- Created
- 2026-07-05
- Stars this week
- +3
You've seen where bw24 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.