-
Notifications
You must be signed in to change notification settings - Fork 68
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
Convert cuda env tgi variables to lmi #2013
Conversation
@@ -47,6 +47,12 @@ translateTGIToLMI "SM_NUM_GPUS" "TENSOR_PARALLEL_DEGREE" | |||
translateTGIToLMI "MAX_CONCURRENT_REQUESTS" "SERVING_JOB_QUEUE_SIZE" | |||
translateTGIToLMI "MAX_BATCH_PREFILL_TOKENS" "OPTION_MAX_ROLLING_BATCH_PREFILL_TOKENS" | |||
translateTGIToLMI "MAX_BATCH_SIZE" "OPTION_MAX_ROLLING_BATCH_SIZE" | |||
translateTGIToLMI "ENABLE_CUDA_GRAPHS" "OPTION_ENFORCE_EAGER" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This one needs to be translated to the opposite value, right? If enable_cuda_graphs = true, enforce_eager = false
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks Sid, https://github.com/vllm-project/vllm/blob/main/vllm/entrypoints/llm.py#L70 You are right,
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Changed it
Description
Translating some of the cuda env variables to LMI format.
Testing:
Bashed into a container and tested this bash script.
bash /usr/local/bin/dockerd-entrypoint.sh serve