Add simple CPU offloading support. #2081
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
janimo
requested review from
merrymercy,
Ying1123,
hnyls2002,
zhyncs,
ispobock and
ByronHsu
as code owners
|
This is the code it is based on vllm-project/vllm#6496 |
merrymercy
reviewed
Nov 23, 2024
merrymercy
reviewed
Nov 23, 2024
merrymercy
approved these changes
Nov 23, 2024
|
@janimo @merrymercy Unit test 3 failed |
@zhyncs it fails in a different test, before the one included in this PR, it seems to be an unrelated OOM present in other CI runs as well. |
This was referenced Nov 29, 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Outdated suggestions cannot be applied.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.
Based on the vLLM implementation, applied to llama.py, gemma2.py and qwen2.py
Tested with unquantized Llama 3.1 8B, Gemma 2 9B and Qwen 2.5 7B on a 6GB RTX 4060.