TrendingRisingGemsRadarToolboxKitsNewsCategoriesAbout

Repository

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.

Open source WebsiteAI & agents Python

Stars

96

Today

+16

last 24 hours

This week

+45

Forks

3

Clone

git clone https://github.com/StartLuxLabs/StartLux-Prism.git

Star growth

2026-10-23: +42026-10-24: +102026-10-25: +112026-10-26: +202026-10-27: +16 (today so far)2026-10-23todaymax +20/day
Stars gained per day since 2026-10-23; the lighter bar is today so far.
#calibration#cuda#cuda-graphs#decision-making#gguf#h200#inference-engine#int8#llm-inference#nvidia
Created
2026-10-13
Last commit
2026-10-22
Gained since tracking
+45

Similar in AI & agents

Updated Tue, 27 Oct 2026 05:10:49 GMT · description from the project itself