Read-only mirror of https://github.com/DCC-BS/vllm — Basel-Stadt. Issues & pull requests at the source.
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Yanick Schraner 6a107c7268
Merge pull request #9 from DCC-BS/renovate/vllm-vllm-openai-0.x
chore(deps): update vllm/vllm-openai docker tag to v0.19.1
2026-04-20 07:51:03 +02:00
.github/workflows chore(deps): update vllm/vllm-openai docker tag to v0.19.1 2026-04-18 09:26:53 +00:00
Dockerfile chore(deps): update vllm/vllm-openai docker tag to v0.19.1 2026-04-18 09:26:53 +00:00
LICENSE Initial commit 2026-02-26 08:05:48 +01:00
README.md feat: Add GitHub Actions workflow, Dockerfile, and README for building and publishing a patched vLLM image with custom transformers. 2026-02-26 08:19:12 +01:00
renovate.json add renovate config 2026-02-26 08:39:35 +01:00

vLLM Patched Image

This repository provides a custom build of vLLM that includes a patched version of the transformers library installed directly from source.

Intent

The primary purpose is to maintain a Docker image compatible with vllm/vllm-openai but with the latest transformers features or fixes from the huggingface/transformers main branch. This is useful when the served model requires a specific transformer version that hasn't been officially released or integrated into the upstream vLLM images yet. An example of such a model is GLM-OCR.

How it works

The Dockerfile uses an ARG BASE_TAG to pull a specific version of vllm/vllm-openai and then updates the transformers package using uv.

CI/CD Workflow

The GitHub Actions workflow Build and Publish Patched vLLM can be triggered manually via workflow_dispatch.

Inputs

  • vllm_tag: The upstream vLLM image tag to use as a base (e.g., v0.7.2-cu124). Defaults to latest.

Outputs

The workflow builds and pushes the image to GitHub Container Registry (GHCR):

  • ghcr.io/DCC-BS/vllm:<vllm_tag>
  • ghcr.io/DCC-BS/vllm:latest

Usage

You can pull the latest patched image:

docker pull ghcr.io/DCC-BS/vllm:latest

Or a specific version:

docker pull ghcr.io/DCC-BS/vllm:v0.16.0-cu130