[Feature] Adding test-deployment-baremetal to the vllm_performance actuator#784
Draft
DanteNiewenhuis wants to merge 5 commits intoIBM:mainfrom
Draft
[Feature] Adding test-deployment-baremetal to the vllm_performance actuator#784DanteNiewenhuis wants to merge 5 commits intoIBM:mainfrom
DanteNiewenhuis wants to merge 5 commits intoIBM:mainfrom
Conversation
…ctly checkes if an endpoint is available, and otherwise throws an VLLMBenchmarkError. However, when trying to serve a model, It is giving a lot of errors.
…en not running already. Currently it is not yet correctly checking if serving is done.
… after runs benchmarks. Still not working: - No alignment with input parameters. - No checking if the correct model is being served (only if any is being served). - vLLM instance is not yet correctly released after the benchmark.
…te to the output metrics of vllm bench
…rving and stopping models as well as handle failing models. The Baremetal deployment seems to function well, but some cleanup is still needed.
Member
|
@DanteNiewenhuis please, let me know when you want me to have another review pass on this PR. |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Started with creating a bare-metal experiment. At the moment, it correctly checks if an endpoint is available and otherwise throws a VLLMBenchmarkError. However, when trying to serve a model, It is giving a lot of errors.