Removed explicit mode for multi-lora #45
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
20 tasks
Tabrizian
reviewed
Jul 3, 2024
| @@ -119,7 +119,6 @@ def _test_vllm_model( | |||
| self.triton_client.stop_stream() | |||
|
|
|||
| def test_multi_lora_requests(self): | |||
| self.triton_client.load_model(self.vllm_model_name) | |||
There was a problem hiding this comment.
Do we know why it doesn't work with explicit mode?
There was a problem hiding this comment.
Due to the way vllm evaluates free GPU memory. I'm not sure what exactly changed, but in explicit mode initialize fails at:
Error in memory profiling. This happens when the GPU memory was not properly cleaned up before initializing the vLLM instance.
Unfortunately, I don't have the capacity to investigate what exactly changed in the profiling
There was a problem hiding this comment.
sample job failure: 98632142
There was a problem hiding this comment.
@oandreeva-nv Have you created ticket for further investigation?
tanmayv25
approved these changes
Jul 5, 2024
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Outdated suggestions cannot be applied.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.
explicit model load was causing failures in tests with vllm==v0.5.0.post1