Skip to content

switch to using formal vllm-cpu image #511

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 3 commits into from
Mar 17, 2025
Merged

switch to using formal vllm-cpu image #511

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7afa7c9
switch to formal vllm-cpu image
nirrozenbaum Mar 17, 2025
ee35a93
documentation of formal vllm-cpu image
nirrozenbaum Mar 17, 2025
a19e7a3
minor updates to cpu deployment
nirrozenbaum Mar 17, 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
10 changes: 7 additions & 3 deletions config/manifests/vllm/cpu-deployment.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@ spec:
spec:
containers:
- name: lora
image: "seedjeffwan/vllm-cpu-env:bb392af4-20250203"
image: "public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.7.2" # formal images can be found in https://gallery.ecr.aws/q9t5s3a7/vllm-cpu-release-repo
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Who owns the release of this image? vllm? what does q9t5s3a7 refer to?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes. vllm owns this image.
see this issue I’ve opened:
vllm-project/vllm#14756

imagePullPolicy: Always
command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
args:
Expand All @@ -23,9 +23,11 @@ spec:
- "--port"
- "8000"
- "--enable-lora"
- "--max-loras"
- "4"
- "--lora-modules"
- '{"name": "tweet-summary-0", "path": "/adapters/hub/models--ai-blond--Qwen-Qwen2.5-Coder-1.5B-Instruct-lora/snapshots/9cde18d8ed964b0519fb481cca6acd936b2ca811"}'
- '{"name": "tweet-summary-1", "path": "/adapters/hub/models--ai-blond--Qwen-Qwen2.5-Coder-1.5B-Instruct-lora/snapshots/9cde18d8ed964b0519fb481cca6acd936b2ca811"}'
- '{"name": "tweet-summary-0", "path": "/adapters/ai-blond/Qwen-Qwen2.5-Coder-1.5B-Instruct-lora_0"}'
- '{"name": "tweet-summary-1", "path": "/adapters/ai-blond/Qwen-Qwen2.5-Coder-1.5B-Instruct-lora_1"}'
env:
- name: PORT
value: "8000"
Expand All @@ -36,6 +38,8 @@ spec:
key: token
- name: VLLM_ALLOW_RUNTIME_LORA_UPDATING
value: "true"
- name: VLLM_CPU_KVCACHE_SPACE
value: "4"
ports:
- containerPort: 8000
name: http
Expand Down