Allocate blocks from id=1 for HPU#160
Merged
kzawora-intel merged 1 commit intoHabanaAI:habana_mainfrom Aug 6, 2024
Merged
Conversation
kzawora-intel
added a commit
that referenced
this pull request
Aug 6, 2024
This reverts commit b43c7f9.
kzawora-intel
added a commit
that referenced
this pull request
Aug 6, 2024
nirda7
pushed a commit
that referenced
this pull request
Aug 6, 2024
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR is related to the change from habana_next: #155
When using BlockManagerV2, blocks are allocated from id=0, which can cause undefined behavior in reuse_and_cache function. This issue is better visible with --tensor-parallel-size > 1.
This change moves the first block id from 0 to 1 for HPU device.