Skip to content

Vllm ray template#103

Open
runpod-ebooks wants to merge 5 commits intomainfrom
vllm-ray-template
Open

Vllm ray template#103
runpod-ebooks wants to merge 5 commits intomainfrom
vllm-ray-template

Conversation

@runpod-ebooks
Copy link
Contributor

A cluster template for a VLLM + Ray workflow for distributed inference. POC for instant clusters

Requires the following environment variables to be specified:
HF_MODEL :: the model to be served, downloaded from huggingface, specified as [username]/[modelname]

Optionally, you can also set a token environment variable if you need models that are gated
HF_TOKEN :: your access token from huggingface

ARG TORCH

RUN python -m pip install --resume-retries 3 --no-cache-dir --upgrade ${TORCH} --index-url https://download.pytorch.org/whl/cu${WHEEL_SRC}
RUN python -m pip install vlla

Choose a reason for hiding this comment

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

typo?

@@ -0,0 +1,9 @@
#Get some information about the cluster properties

Choose a reason for hiding this comment

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

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants