Skip to content

LLM: update to vllm version 0.11.0, upgrade to cuda 12.9.1 #831

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
ad-astra-video wants to merge 5 commits into
base: main
Choose a base branch
from
Open

LLM: update to vllm version 0.11.0, upgrade to cuda 12.9.1 #831

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
336e314
LLM: update to vllm version 0.11.0, upgrade to cuda 12.8.1 for docker…
ad-astra-video Oct 28, 2025
31a51b3
revert PIP_VERSION change
ad-astra-video Oct 28, 2025
4783f1f
update tensor and pipeline parallelism confirmation to be more forgiving
ad-astra-video Oct 28, 2025
206a1a8
remove max_num_batched_tokens check against max_model_len. chunked pr…
ad-astra-video Oct 28, 2025
6c40af8
add /chat/completions overload route for llm
ad-astra-video Oct 28, 2025
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
8 changes: 4 additions & 4 deletions runner/docker/Dockerfile.llm
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
# Based on https://github.com/huggingface/api-inference-community/blob/main/docker_images/diffusers/Dockerfile

FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu20.04
LABEL maintainer="Yondon Fu <yondon@livepeer.org>"
FROM nvidia/cuda:12.9.1-cudnn-devel-ubuntu22.04


# Add any system dependency here
# RUN apt-get update -y && apt-get install libXXX -y
Expand Down Expand Up @@ -30,8 +30,8 @@ RUN pyenv install $PYTHON_VERSION && \

# Upgrade pip and install your desired packages
ARG PIP_VERSION=24.2
RUN pip install --no-cache-dir --upgrade pip==${PIP_VERSION} setuptools==69.5.1 wheel==0.43.0 && \
pip install --no-cache-dir torch==2.4.0 torchvision torchaudio pip-tools
RUN pip install --no-cache-dir --upgrade pip>=${PIP_VERSION} setuptools>=69.5.1 wheel>=0.43.0 && \
pip install --no-cache-dir torch>=2.4.0 torchvision torchaudio pip-tools

ARG VERSION="undefined"
ENV VERSION=${VERSION}
Expand Down
2 changes: 1 addition & 1 deletion runner/requirements.llm.in
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
vllm==0.10.0
vllm==0.11.0
diffusers
accelerate
transformers
Expand Down
Loading
Loading