vLLM v0.34.0rc1
vLLM v0.34.0rc1 is tagged, a release candidate with a bugfix for greedy_argmax on XPU. Correction, : this row first said it was released; its source is a GitHub tag with no published release, and none is published as of .
The Deploy Log | Products | Free, no signup
vLLM changelog
6 versions of vLLM from vLLM in The Deploy Log. From to . On the median a new version every 13 days, publisher's dates only; the longest wait was 36 days. The newest is v0.34.0rc1. 1 version in the last 30 days. 2 rows with no publisher's date. Each links the publisher's own page.
| Version | Publisher's date | Days after the one before |
|---|---|---|
| v0.34.0rc1 | 36 | |
| v0.31.1rc0 | 13 | |
| v0.31.0 | No date | |
| v0.30.1rc0 | 1 | |
| v0.30.0 | ||
| v0.30.0rc2 | No date |
vLLM v0.31.1rc0
vLLM v0.31.1rc0 exposes cached prompt tokens by cache tier in metrics.
vLLM v0.31.0
vLLM v0.31.0 adds a Transformers version upper bound in requirements.
vLLM v0.30.1rc0
vLLM v0.30.1rc0 adds MI355 dense NVFP4 and MoRI kernel mirrors.
vLLM v0.30.0
vLLM v0.30.0 fixes DeepGEMM CUDA 12.9 release builds.
vLLM v0.30.0rc2
vLLM v0.30.0rc2 tagged a bugfix to avoid receive reports for notification-only requests in NIXL.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.