Skip to content

Update dependencies to new inference engine versions #185

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
XkunW wants to merge 9 commits into
base: main
Choose a base branch
from
+3,954 −1,623
Open

Update dependencies to new inference engine versions #185

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
416077e
Update dependencies to new inference engine versions
XkunW Jan 21, 2026
5431aac
Merge branch 'main' into f/update-dep
XkunW Jan 21, 2026
b8cc438
Add audio support
XkunW Jan 22, 2026
5c0a218
Add vllm bench support
XkunW Jan 23, 2026
2b463d8
Explicitly add torch-codec to better support audio
XkunW Jan 23, 2026
c19f60f
Add ffmpeg related packages
XkunW Jan 23, 2026
3c56522
Add more ffmpeg related packages and ffmpeg
XkunW Jan 23, 2026
512f69f
Add ax and wandb to support engine tuning, add nvml to support GPU us…
XkunW Jan 23, 2026
45e87c4
Change torchcodec to a pytorch 2.9 compatible version
XkunW Jan 24, 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
8 changes: 7 additions & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
[project]
name = "vec-inf"
version = "0.8.0"
version = "0.8.1"
description = "Efficient LLM inference on Slurm clusters using vLLM."
readme = "README.md"
authors = [{name = "Marshall Wang", email = "marshall.wang@vectorinstitute.ai"}]
Expand Down Expand Up @@ -42,6 +42,9 @@ inference = [
"torch>=2.7.0",
"cupy-cuda12x>=12.3.0",
"flashinfer-python>=0.4.0",
"ax-platform>=1.1.0",
"py3nvml",
"wandb>=0.17.0",
]

[project.optional-dependencies]
Expand All @@ -50,6 +53,9 @@ inference = [
vllm = [
"vllm>=0.11.2",
"ray[default]>=2.51.0",
"vllm[audio]",
"vllm[bench]",
"torchcodec>=0.9.0,<0.10.0",
]
# SGLang inference backend (conflicts with vllm due to dependency version conflicts)
# Install with: uv sync --extra sglang --group inference
Expand Down
2 changes: 1 addition & 1 deletion sglang.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ RUN apt-get update && apt-get install -y \
wget build-essential libssl-dev zlib1g-dev libbz2-dev \
libreadline-dev libsqlite3-dev libffi-dev libncursesw5-dev \
xz-utils tk-dev libxml2-dev libxmlsec1-dev liblzma-dev libnuma1 \
git vim \
git vim ffmpeg libavcodec-dev libavformat-dev libavutil-dev libswscale-dev libswresample-dev \
&& rm -rf /var/lib/apt/lists/*

# Install Python
Expand Down
Loading