Skip to content
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.

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

[Serve][Feature] Ability to use mathematical operations in variable assignment #4982

Open
JGSweets opened this issue Mar 18, 2025 · 0 comments

Comments

@JGSweets
Copy link
Contributor

Ideally we would not have to use linux commands to do mathematical operations such as multiply or divide.

Below uses one of the examples from the Skypilot documentation to illustrate the current vs desired state.


Current State

# service.yaml
.
.
.
run: |
  conda activate vllm
  PIPELINE_PARALLEL_SIZE=2
  TENSOR_PARALLEL_SIZE=$(($SKYPILOT_NUM_GPUS_PER_NODE / 2 ))
  python -m vllm.entrypoints.openai.api_server \
    --tensor-parallel-size $TENSOR_PARALLEL_SIZE \
    --pipeline-parallel-size $PIPELINE_PARALLEL_SIZE \
    --host 0.0.0.0 --port 8080 \
    --model mistralai/Mixtral-8x7B-Instruct-v0.1

Ideal State

# service.yaml
.
.
.
run: |
  conda activate vllm=
  python -m vllm.entrypoints.openai.api_server \
    --tensor-parallel-size ${SKYPILOT_NUM_GPUS_PER_NODE / 2} \
    --pipeline-parallel-size 2 \
    --host 0.0.0.0 --port 8080 \
    --model mistralai/Mixtral-8x7B-Instruct-v0.1

${SKYPILOT_NUM_GPUS_PER_NODE / 2} could be altered, but ideally it would be something inline like this for cleanliness.

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

No branches or pull requests

1 participant