vLLM v0.34.0
v0.34.0 1,061 commits from 412 contributors (120 new). Thank you! …
What moved
v0.34.0 1,061 commits from 412 contributors (120 new). Thank you! TL;DR 10 new models (Mistral Large 4, MiniMax-M3.1-Flash, Nemotron-3.5-Transcribe, and more!) Extensible KV cache is on by default: vLLM sizes the KV cache from memory actually free after warmup, so most models get a bigger cache and more throughput. …
Why it matters
Filed as a public note from vLLM, 2026-11-16. The desk tags this brief LLM / Hardware.
On the record
- Filed from the vLLM official GitHub releases feed on 2026-11-16.
- Primary source host: github.com.
- v0.34.0 1,061 commits from 412 contributors (120 new).
Primary source
github.com
github.com
Desk
Logged as brief 6630
Logged as brief 6630
Cite this brief
vLLM v0.34.0 (vLLM, 2026-11-16) — https://labledgerdesk.pages.dev/b/2026/11/16/vllm-v0-34-0/