Skip to content

[v1] vLLM 0.11.1 #5482

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
merged 14 commits into from
Nov 19, 2025
+31 −30
Merged

[v1] vLLM 0.11.1 #5482

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
865da11
add dockerfile and buildspec
jinyan-li1 Nov 18, 2025
edae5fb
update dev toml
jinyan-li1 Nov 18, 2025
b7b6606
ec2 build and test
jinyan-li1 Nov 18, 2025
01833df
try prior nightly
jinyan-li1 Nov 18, 2025
0a4d2b4
increase ec2 test timeout
jinyan-li1 Nov 18, 2025
59ef6d9
rebuild sm image
jinyan-li1 Nov 18, 2025
96b56f6
vo.11.1
junpuf Nov 19, 2025
156f01a
update image
junpuf Nov 19, 2025
0f4d8e6
skip outdated tests
junpuf Nov 19, 2025
e203409
update
junpuf Nov 19, 2025
e04c32d
update
junpuf Nov 19, 2025
6772e24
use new AMI
junpuf Nov 19, 2025
2d79c6e
update
junpuf Nov 19, 2025
8194e81
Merge branch 'master' into vllm-0.11.1-pre
junpuf Nov 19, 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
18 changes: 9 additions & 9 deletions release_images_general.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,24 +58,24 @@ release_images:
public_registry: True
5:
framework: "vllm"
version: "0.11.0"
version: "0.11.1"
arch_type: "x86"
customer_type: "ec2"
general:
device_types: [ "gpu" ]
python_versions: [ "py312" ]
os_version: "ubuntu22.04"
cuda_version: "cu128"
cuda_version: "cu129"
example: False
disable_sm_tag: False
force_release: False
public_registry: True
enable_soci: True
6:
framework: "vllm"
version: "0.10.2"
arch_type: "arm64"
customer_type: "ec2"
version: "0.11.1"
arch_type: "x86"
customer_type: "sagemaker"
general:
device_types: [ "gpu" ]
python_versions: [ "py312" ]
Expand All @@ -88,14 +88,14 @@ release_images:
enable_soci: True
7:
framework: "vllm"
version: "0.11.0"
arch_type: "x86"
customer_type: "sagemaker"
version: "0.10.2"
arch_type: "arm64"
customer_type: "ec2"
general:
device_types: [ "gpu" ]
python_versions: [ "py312" ]
os_version: "ubuntu22.04"
cuda_version: "cu128"
cuda_version: "cu129"
example: False
disable_sm_tag: False
force_release: False
Expand Down
1 change: 1 addition & 0 deletions test/vllm/sagemaker/test_sm_endpoint.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,7 @@ def deploy_endpoint(name, image_uri, role, instance_type):
instance_type=instance_type,
initial_instance_count=1,
endpoint_name=name,
inference_ami_version="al2-ami-sagemaker-inference-gpu-3-1",
wait=True,
)
print("Endpoint deployment completed successfully")
Expand Down
6 changes: 3 additions & 3 deletions vllm/buildspec-sm.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ account_id: &ACCOUNT_ID <set-$ACCOUNT_ID-in-environment>
prod_account_id: &PROD_ACCOUNT_ID 763104351884
region: &REGION <set-$REGION-in-environment>
framework: &FRAMEWORK vllm
version: &VERSION "0.11.0"
version: &VERSION "0.11.1"
short_version: &SHORT_VERSION "0.11"
arch_type: &ARCH_TYPE x86_64
autopatch_build: "False"
Expand Down Expand Up @@ -35,7 +35,7 @@ images:
<<: *BUILD_CONTEXT
image_size_baseline: 26000
device_type: &DEVICE_TYPE gpu
cuda_version: &CUDA_VERSION cu128
cuda_version: &CUDA_VERSION cu129
python_version: &DOCKER_PYTHON_VERSION py3
tag_python_version: &TAG_PYTHON_VERSION py312
os_version: &OS_VERSION ubuntu22.04
Expand All @@ -50,4 +50,4 @@ images:
- sanity
- security
- sagemaker
- eks
# - eks
34 changes: 17 additions & 17 deletions vllm/buildspec.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@ account_id: &ACCOUNT_ID <set-$ACCOUNT_ID-in-environment>
prod_account_id: &PROD_ACCOUNT_ID 763104351884
region: &REGION <set-$REGION-in-environment>
framework: &FRAMEWORK vllm
version: &VERSION "0.11.0"
version: &VERSION "0.11.1"
short_version: &SHORT_VERSION "0.11"
arch_type: &ARCH_TYPE x86_64
autopatch_build: "False"
Expand Down Expand Up @@ -35,7 +35,7 @@ images:
<<: *BUILD_CONTEXT
image_size_baseline: 26000
device_type: &DEVICE_TYPE gpu
cuda_version: &CUDA_VERSION cu128
cuda_version: &CUDA_VERSION cu129
python_version: &DOCKER_PYTHON_VERSION py3
tag_python_version: &TAG_PYTHON_VERSION py312
os_version: &OS_VERSION ubuntu22.04
Expand All @@ -49,19 +49,19 @@ images:
test_platforms:
- sanity
- security
- ec2
- eks
tests:
- platform: ec2-multi-node-efa
params:
instance_type: p4d.24xlarge
node_count: 2
run:
- python test/v2/ec2/vllm/test_ec2.py
# - ec2
# - eks
# tests:
# - platform: ec2-multi-node-efa
# params:
# instance_type: p4d.24xlarge
# node_count: 2
# run:
# - python test/v2/ec2/vllm/test_ec2.py

# - platform: eks
params:
cluster: dlc-vllm
namespace: vllm
run:
- python test/v2/eks/vllm/vllm_eks_test.py
# # - platform: eks
# params:
# cluster: dlc-vllm
# namespace: vllm
# run:
# - python test/v2/eks/vllm/vllm_eks_test.py
2 changes: 1 addition & 1 deletion vllm/x86_64/gpu/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
FROM docker.io/vllm/vllm-openai:v0.11.0 as base
FROM docker.io/vllm/vllm-openai:v0.11.1 as base
ARG PYTHON="python3"
LABEL maintainer="Amazon AI"
ARG EFA_VERSION="1.43.3"
Expand Down