Skip to content

[docker] Update stable image to vllm==0.15.1 #5221

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Begunner wants to merge 11 commits into
base: main
Choose a base branch
from
+28 −24
Open

[docker] Update stable image to vllm==0.15.1 #5221

Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
8fc4203
use vllm015
Feb 5, 2026
5d6695b
vllm0151
Feb 5, 2026
67f1659
skip apex cuda version check
Feb 5, 2026
5f89aaf
preinstall torch2.9.1+cu129
Feb 5, 2026
57ce4a9
add cu129
Feb 5, 2026
17420a4
limit transformers version
Feb 6, 2026
7168447
modify test
Feb 6, 2026
aa5557f
mistake
Feb 6, 2026
9c3cc77
fix test
Feb 6, 2026
81d483f
update readme
Feb 6, 2026
13c1c2c
update ci
Feb 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
add cu129
  • Loading branch information
Begunner committed Feb 5, 2026
commit 57ce4a98d14f1e5b66696670428afc131d177883
2 changes: 1 addition & 1 deletion docker/Dockerfile.stable.vllm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ RUN pip install torch==2.9.1 torchvision torchaudio --index-url https://download
RUN pip install vllm==0.15.1
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Feb 6, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

critical

Installing vllm without the --no-deps flag may lead to its dependencies, including torch, being installed. This could potentially override the specific torch==2.9.1 version installed in the preceding step. If the torch version changes, the sed command on line 35 will fail as its path is hardcoded for torch-2.9.1+cu129.dist-info. The previous installation method for vllm used --no-deps, suggesting that dependencies are managed elsewhere. To prevent the build from breaking, you should add the --no-deps flag to this installation command.

RUN pip install --no-deps vllm==0.15.1

Copy link
Contributor

@thvasilo thvasilo Feb 7, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

+1 here, it's usually safer to fully determine vllm 0.15.1 dependencies, install those first, and install vllm with --no-deps.

You can figure out vllm deps using something like

uv venv --python 3.12 --seed
source .venv/bin/activate
uv pip install vllm==0.15.1
uv pip show vllm

and can then pin the specific version shown by uv pip list


# use cudnn9.16 to avoid conflict
RUN sed -i '/nvidia-cudnn-cu12/d' /usr/local/lib/python3.12/dist-packages/torch-2.9.1.dist-info/METADATA
RUN sed -i '/nvidia-cudnn-cu12/d' /usr/local/lib/python3.12/dist-packages/torch-2.9.1+cu129.dist-info/METADATA
RUN pip install --no-deps --force-reinstall nvidia-cudnn-cu12==9.16.0.29

RUN pip install pybind11
Expand Down