Python
StartLuxLabs/StartLux-Prism
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
★ 292
Stars
5 forks · 3 open issues
+20/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
46.8
Momentum / 100
see the breakdown below
25d ago
Created
last push 12d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 25.4 | +20/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 14.2 | last push 12d ago; decays to zero at 180 days |
| Scale | 15 | 7.2 | 292 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 46.8 | sum of the above |
Detail
| Topics | calibrationcudacuda-graphsdecision-makingggufh200inference-engineint8llm-inferencenvidiaquantizationstartlux |
| Matched on | LLM & Inference (llm-inference) |
| Short window | +142 stars over 7 days = 20.3/day |
| Long window | no snapshot 14–45 days old yet |
| Lifetime average | 12.83 stars/day over 23 days |
| First seen here | 2026-10-23 |
| Last read | 2d ago |