LocalVLLMModel and deployment handler #102
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
michaelharrisonmai
requested review from
vidhishanair,
gugarosa,
safooray and
piero2c
gugarosa
previously approved these changes
Mar 5, 2025
added 3 commits
March 6, 2025 13:15
…soft/eureka-ml-insights into mharrison/local-vllm-model
|
@microsoft-github-policy-service agree company="Microsoft" |
safooray
reviewed
Mar 7, 2025
safooray
reviewed
Mar 7, 2025
safooray
reviewed
Mar 7, 2025
added 5 commits
March 12, 2025 19:45
safooray
reviewed
Mar 15, 2025
added 2 commits
March 15, 2025 18:27
Merge branch 'main' into mharrison/local-vllm-model
safooray
approved these changes
Mar 17, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR introduces the
LocalVLLMModelandLocalVLLMDeploymentHandler, the former is a usual Model (i.e. implements generate) and the latter is a new class to handle aspects of deployment (deployment itself, health checks on your deployment, shutdown of servers).Use LocalVLLMModel either by defining a ModelConfig or by passing info in the command line so that vllm can recognize your deployment or even deploy for you.
If you have already deployed, pass "ports" parameter, otherwise the LocalVLLMDeploymentHandler will spin up "num_servers" (default = 1) servers for you, wait for deployment to finish, and continue with the eval pipeline.