GIT_FEED

quantumaikr/quant.cpp

Embeddable LLM inference in pure C. 33K LOC, zero dependencies. Delta KV compression — 4x longer context. Inspired by TurboQuant (ICLR 2026).

View on GitHub
0Active

On the radar — signal detected

Stars
154
Forks
26
Contributors
0
Language
C

Score updated Apr 4, 2026

// SUBSCRIBE

The repos that moved this week, why they matter, and what to watch next. One email. No noise.