Skip to content

feat: Upgrade to vLLM 0.15.0 and upgrade dependencies #122

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

Merged
JustinPerlman merged 2 commits into from
Feb 2, 2026
Merged

feat: Upgrade to vLLM 0.15.0 and upgrade dependencies #122

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4c733d8
feat: Bump vllm/flashinfer, base images, DeepGEMM
JustinPerlman Feb 2, 2026
9e47e66
feat: Add grpcio-tools to vllm builder deps
JustinPerlman Feb 2, 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: 4 additions & 4 deletions .github/configurations/vllm-tensorizer.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
vllm-commit:
- 'v0.12.0'
- 'v0.15.0'
flashinfer-commit:
- 'v0.5.3'
- 'v0.6.1'
builder-base-image:
- 'ghcr.io/coreweave/ml-containers/torch:19331b7-nccl-cuda12.9.1-ubuntu22.04-nccl2.29.2-1-torch2.9.1-vision0.24.1-audio2.9.1-abi1'
- 'ghcr.io/coreweave/ml-containers/torch:17ad6db-nccl-cuda12.9.1-ubuntu22.04-nccl2.29.2-1-torch2.10.0-vision0.25.0-audio2.10.0-abi1'
final-base-image:
- 'ghcr.io/coreweave/ml-containers/torch:19331b7-nccl-cuda12.9.1-ubuntu22.04-nccl2.29.2-1-torch2.9.1-vision0.24.1-audio2.9.1-abi1'
- 'ghcr.io/coreweave/ml-containers/torch:17ad6db-nccl-cuda12.9.1-ubuntu22.04-nccl2.29.2-1-torch2.10.0-vision0.25.0-audio2.10.0-abi1'
4 changes: 2 additions & 2 deletions vllm-tensorizer/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,7 @@ RUN git clone --filter=tree:0 --no-single-branch --no-checkout \

FROM alpine/git:2.36.3 AS deepgemm-downloader
WORKDIR /git
ARG DEEPGEMM_COMMIT='594953acce41793ae00a1233eb516044d604bcb6'
ARG DEEPGEMM_COMMIT='0f5f2662027f0db05d4e3f6a94e56e2d8fc45c51'
RUN git clone --filter=tree:0 --no-single-branch --no-checkout \
https://github.com/deepseek-ai/DeepGEMM && \
cd DeepGEMM && \
Expand All @@ -107,7 +107,7 @@ FROM builder-base AS vllm-builder
RUN --mount=type=bind,from=vllm-downloader,source=/git/vllm,target=/workspace,rw \
. /opt/arch_flags.sh && \
if [ -z "$MAX_JOBS" ]; then unset MAX_JOBS; fi && \
python3 -m pip install --no-cache-dir py-cpuinfo 'cmake>=3.26.1,<4' && \
python3 -m pip install --no-cache-dir py-cpuinfo 'cmake>=3.26.1,<4' grpcio-tools && \
if [ -f 'use_existing_torch.py' ]; then \
python3 use_existing_torch.py; \
else \
Expand Down
Loading