stars 1 stars 2 stars 3

thaw is the fork() primitive for live LLM inference. snapshot a running session — weights, KV cache, and scheduler state — into a portable file, then fork N children that skip the cold prefill and diverge from the fork point. on an H100, a pre-warmed pool forks at 0.88s median per round versus a ~340s cold boot, bit-identical at the fork boundary. open source, pip-installable, works with vLLM and SGLang. we contribute upstream (vLLM fork/snapshot RFC #34303) and publish our research (re-feeding is not replaying, arXiv:2606.15621). built for RL post-training, parallel coding agents, and multi-agent systems — anywhere you fork from a shared context and pay the prefill tax on every branch.

Website https://thaw.sh
Employees 5 (1 on RocketReach)
Founded 2026
Industry Software Development

thaw Questions

Matthew Yu is the Co-Founder of thaw.

1 people are employed at thaw.

thaw is based in San Jose, California.

Top thaw Employees

G2 Leader Summer 2026 G2 Best Est ROI Mid-Market Summer 2026 G2 Easiest Admin Mid-Market Summer 2026 G2 Most Implementable Summer 2026 G2 Best Results Mid-Market Summer 2026 G2 Lead Capture Mid-Market Summer 2026 Inc Fastest Growing Private Companies 2026 Inc Best Workplace 2026
g2crowd
G2Crowd Trusted
chromestore
300K+ Plugin Users