fix(mig): fallback gpu_memory_total value#3353
Closed
tomheno wants to merge 1 commit intosgl-project:mainfrom
Closed
fix(mig): fallback gpu_memory_total value#3353tomheno wants to merge 1 commit intosgl-project:mainfrom
tomheno wants to merge 1 commit intosgl-project:mainfrom
Conversation
tomheno
requested review from
ByronHsu,
Ying1123,
hnyls2002,
ispobock,
merrymercy and
zhyncs
as code owners
Collaborator
|
@dsingal0 what do you think? |
Contributor
|
can you resolve the conflicts? |
Author
|
Hi, I did solve conflict @merrymercy |
Contributor
|
Fix in #8167. |
Collaborator
|
Thanks for the contribution! |
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
It's currently not possible to run on on MiG paritionned GPU as those have insufficient permission when using nvidia-smi cli to access available memory.
Tested on H100 & H200.
See #2933
Modifications
Added a
SGLANG_GPU_MEMORY_TOTAL_FALLBACKenvironment variable to manually set available memory when nvidia-smi is not possible