[FIX] Gradlib OOM on Navi and sometimes on MI #124
Merged
Conversation
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
added 2 commits
August 7, 2024 23:22
…nvalidation buffers
gshtras
approved these changes
Aug 8, 2024
AdrianAbeyta
pushed a commit
that referenced
this pull request
Aug 12, 2024
* add memory clean up after every shape and parameter to reduce cache invalidation buffers * small typo * syntax change --------- Co-authored-by: maleksan85 <[email protected]>
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Outdated suggestions cannot be applied.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.
add memory clean up after every shape tryout and a parameter to reduce number of cache invalidation buffers
command like: CACHE_INVALIDATE_BUFFERS=11 python3 vllm/gradlib/gradlib/gemm_tuner.py --input_file /root/workspace/gradlib/gemms_1_2048_512.csv --tuned_file /root/workspace/gradlib/gemms_tuned_1_2048_512.csv --indtype f16 --outdtype f16
works on Navi32 well for llama2 7b