Firmwarely
Devices / Self-hosted apps & servers / vLLM LLM inference server

vLLM LLM inference server releases

new version

vLLM LLM inference server is tracked under self-hosted apps & servers. Its latest version, 0.33.0, shipped on Nov 2, 2026. Firmwarely has recorded 5 versions since Sep 9, 2026.

Latest version
0.33.0
Released
Category
Self-hosted apps & servers
Last checked

How to update vLLM LLM inference server

Open update page ↗
  1. Read the release notes first — self-hosted projects break config and schemas between versions more often than appliances do.
  2. Docker: pull the new image tag and recreate the container (`docker compose pull && docker compose up -d`).
  3. Package or bare metal: update through your distribution's package manager, or replace the binary from the releases page.
  4. Back up the config and database directory first. For most projects a downgrade is not supported once the schema has migrated.

Always install releases from the project itself. Firmwarely links out; it never hosts downloads.

What changed

v0.33.0: Highlights: This release features 927 commits from 389 contributors (122 new)! New models: Reflection Beam-1.0 (501B MoE, 23B active) with its DFlash2 drafter (#​62074), Yandex AliceAI-Foundation-80B-A3B (#​57963), Recursive Flint (40B MoE, 2.5B active) (#​62938), Muse Spark Open (#​61879)…

Release notes ↗

Version history

0.33.0
0.32.0
0.31.0
0.30.0
0.29.0

FAQ

What is the latest version of vLLM LLM inference server?

Version 0.33.0, released Nov 2, 2026. This page is refreshed every hour from the project's release page.

How do I update vLLM LLM inference server?

See the step-by-step above. Pull the new image or package and restart the service. Read the release notes and back up the data directory first; most projects can't downgrade once the database has migrated.

How does Firmwarely know when there's a new version?

Every hour we read the project's official release page for vLLM LLM inference server and record the version, date and changelog. Subscribers watching it get an email when it changes: the next morning on Pro, in the Monday roundup on the free plan.

Is this an official vLLM page?

No. Firmwarely is independent. Project and product names belong to their owners; always install releases from the project's own source.

Recently updated in Self-hosted apps & servers

All self-hosted apps & servers →

Get alerts for vLLM LLM inference server

One email when a new release or a security fix ships: weekly and free for up to 3 devices, daily on Pro.