Skip to content

refactor(cuda & rocm): bump vllm to v0.20.2 #157

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
gitlawr wants to merge 2 commits into
base: main
Choose a base branch
from
Open

refactor(cuda & rocm): bump vllm to v0.20.2 #157

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
478b4b2
refactor(cuda/rocm): bump vllm to 0.20.2
gitlawr May 21, 2026
86022f2
fix(make): honor service-specific Dockerfile in package target
gitlawr May 21, 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
2 changes: 1 addition & 1 deletion Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,7 +142,7 @@ package:
--platform "$${JOB_PLATFORM}" \
--target "$${JOB_TARGET}" \
--tag "$${JOB_TAG}" \
--file "$${JOB_LOCATION}/Dockerfile" \
--file "$${JOB_DOCKERFILE}" \
--attest "type=provenance,disabled=true" \
--attest "type=sbom,disabled=true" \
--ulimit nofile=65536:65536 \
Expand Down
4 changes: 2 additions & 2 deletions pack/cuda/Dockerfile.vllm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,8 @@ ARG PYTHON_VERSION=3.12
ARG CMAKE_MAX_JOBS
ARG CUDA_VERSION=13.0.1
ARG CUDA_ARCHS
ARG VLLM_BASE_IMAGE=vllm/vllm-openai:v0.20.1
ARG VLLM_VERSION=0.20.1
ARG VLLM_BASE_IMAGE=vllm/vllm-openai:v0.20.2
ARG VLLM_VERSION=0.20.2
ARG VLLM_TORCH_VERSION=2.12.0
ARG VLLM_TORCH_CUDA_VERSION=${CUDA_VERSION}
ARG VLLM_OMNI_COMMIT=704b6bb6
Expand Down
12 changes: 6 additions & 6 deletions pack/matrix.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,8 +60,8 @@ rules:
- "linux/amd64"
args:
- "ROCM_VERSION=7.2.1"
- "VLLM_VERSION=0.20.1"
- "VLLM_BASE_IMAGE=vllm/vllm-openai-rocm:v0.20.1"
- "VLLM_VERSION=0.20.2"
- "VLLM_BASE_IMAGE=vllm/vllm-openai-rocm:v0.20.2"

#
# NVIDIA CUDA
Expand All @@ -74,17 +74,17 @@ rules:
- "vllm"
args:
- "CUDA_VERSION=13.0.1"
- "VLLM_VERSION=0.20.1"
- "VLLM_BASE_IMAGE=vllm/vllm-openai:v0.20.1-ubuntu2404"
- "VLLM_VERSION=0.20.2"
- "VLLM_BASE_IMAGE=vllm/vllm-openai:v0.20.2-ubuntu2404"
## NVIDIA CUDA 12.9.1
##
- backend: "cuda"
services:
- "vllm"
args:
- "CUDA_VERSION=12.9.1"
- "VLLM_VERSION=0.20.1"
- "VLLM_BASE_IMAGE=vllm/vllm-openai:v0.20.1-cu129-ubuntu2404"
- "VLLM_VERSION=0.20.2"
- "VLLM_BASE_IMAGE=vllm/vllm-openai:v0.20.2-cu129-ubuntu2404"

#
# Iluvatar CoreX
Expand Down
4 changes: 2 additions & 2 deletions pack/rocm/Dockerfile.vllm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,8 @@ ARG PYTHON_VERSION=3.12
ARG CMAKE_MAX_JOBS
ARG ROCM_VERSION=7.2.1
ARG ROCM_ARCHS
ARG VLLM_BASE_IMAGE=vllm/vllm-openai-rocm:v0.20.1
ARG VLLM_VERSION=0.20.1
ARG VLLM_BASE_IMAGE=vllm/vllm-openai-rocm:v0.20.2
ARG VLLM_VERSION=0.20.2
ARG VLLM_TORCH_VERSION=2.10.0
ARG VLLM_TORCH_ROCM_VERSION=${ROCM_VERSION}
ARG VLLM_LMCACHE_VERSION=0.4.4
Expand Down
Loading