Conversation
Qubitium
commented
Apr 2, 2026
| # The local env does not ship Marlin runtime kernels, so validation reloads must stay on Torch. | ||
| LOAD_BACKEND = BACKEND.TORCH | ||
| # Gemma 4 full-attention layers expand to 512-dim heads, which FlashAttention cannot execute. | ||
| USE_FLASH_ATTN = False |
Collaborator
Author
There was a problem hiding this comment.
Gemma4 does not work with FA2. Is this a HF model upload issue due to the Gemma4 variants or Transformers just made up some bad unit tests?
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.