[ROCm] include gfx908 as supported #2792
Merged
+1
−1
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
jamestwhedbee
changed the title
Closed
|
@zhuohan123 would you have time to review this? |
|
@WoosukKwon is there anything I should be doing differently to get a review here? |
xjpang
pushed a commit
to xjpang/vllm
that referenced
this pull request
Feb 22, 2024
xjpang
pushed a commit
to xjpang/vllm
that referenced
this pull request
Mar 4, 2024
get this error in MI100: |
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Outdated suggestions cannot be applied.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.
ROCm/flash-attention supports the
gfx908architecture.Without this change, vLLM appears to build successfully for me, but serving an LLM on an MI100 results in gibberish output.
With this change, everything works as expected.