Skip to content

Thaw

v0.2.0 Breaking

This release includes 1 breaking change for platform teams planning a safe upgrade.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agents inference kv-cache llm reinforcement-learning sglang
+1 more
vllm

Affected surfaces

auth rce_ssrf

Summary

AI summary

Removes the VLLM_ENABLE_V1_MULTIPROCESSING=0 requirement, enabling thaw under vLLM's default V1 multiprocessing mode.

Full changelog

Summary

  • Removes the VLLM_ENABLE_V1_MULTIPROCESSING=0 requirement for freeze / restore / load / pool / TP.
  • thaw now works under vLLM's default V1 multiprocessing mode.
  • KV cache path still sets V1 MP=0 internally (scheduler state only reachable in V1-inproc/V0) — users don't have to know.
  • Auto-sets VLLM_ALLOW_INSECURE_SERIALIZATION=1 on import so vLLM 0.19's msgspec IPC accepts function callables via cloudpickle fallback.

Validation

2×A40 RunPod, vLLM 0.19.0, Llama-3-8B:

  • [x] weights-only freeze under V1 MP default
  • [x] thaw_vllm.load() + generate under V1 MP default
  • [x] thaw serve pool + slot-warm + two completions
  • [x] TP=2 freeze + restore under V1 MP default
  • [x] KV cache regression (conditional V1 MP=0 auto-set still works)

5/5 pass.

Test plan

  • [ ] Merge
  • [ ] Update README to drop the env-var note
  • [ ] Bump minor version on PyPI

Breaking Changes

  • Removed requirement for `VLLM_ENABLE_V1_MULTIPROCESSING=0`; thaw now works under vLLM's default V1 multiprocessing mode.

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track Thaw

Get notified when new releases ship.

Sign up free

Beta — feedback welcome: [email protected]