thaw-vllm
The fork primitive for LLM inference. Snapshot a running session — weights + KV cache + scheduler state — and hydrate it into N divergent children that skip prefill. For RL rollouts, parallel coding agents, agent branching. Supports vLLM and SGLang.
thaw-vllm has been downloaded 9,245 times in total on PyPI, including 801 in the last 30 days. The latest version is 0.5.1, released Apr 23, 2026. It is distributed under the Apache-2.0 license.
Version0.5.1
Downloads
9.24k
LicenseApache-2.0
AuthorNils Matteson
Downloads
Weekly, last 90d.
Includes CI traffic.
VersionsTotal0.*
Range
View
Granularity
Group by
CI traffic
Stack: OffCI: Included2 / 17 series
Selected total18.49k
9.2kAll-time
801Last 30 days
13Last 24 h
<0.01/sPer second
Sponsored
Sponsorships keep pepy free to read
Version distribution
Share of downloads by released version. Computed over the last quarter.
- 018.9%
0.5.1
825 downloadsDownloads8258.9% - 028.8%
0.3.0
814 downloadsDownloads8148.8% - 037.5%
0.1.0
695 downloadsDownloads6957.5% - 047.4%
0.2.1
680 downloadsDownloads6807.4% - 056.5%
0.6.0
602 downloadsDownloads6026.5% - 066.4%
0.5.0
590 downloadsDownloads5906.4% - 075.9%
0.1.4
542 downloadsDownloads5425.9% - 085.9%
0.2.0
542 downloadsDownloads5425.9% - 0942.8%
Other
4.0k downloadsDownloads4.0k42.8%
Guess the next day
Thirteen recent days of thaw-vllm downloads. Drag the green handle on the right to guess where day fourteen lands.