Fixing trtllm OOM Issue #91
Closed
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
…el support sections in README, add some better checks and error messages around --source arg, add 'local:' source prefix for parity, bump version to 0.1.0dev so it's easier to have 'patch' versions
…be restored in 24.10
… ensure server is cleaned properly between tests
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Outdated suggestions cannot be applied.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.
Currently, when building the engine with the TRTLLM HLAPI leads to OOM issues when starting the server.
The root cause appears to be something not being cleaned up post-engine creation in
tensorrt_llm.In order to resolve this, we separate engine building for HLAPI into a separate child process and allow the operating system to clean up any dangling allocations that are currently not being cleaned up.