fix: ensure LTXAVTEModel uses half-precision for SageAttention compat… #11898
+20
−6
Conversation
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
…ibility - Add automatic detection and default to bfloat16 (or fp16 fallback) when no explicit dtype is provided, based on device capabilities - Respect provided dtype_llama/dtype consistently across Gemma model, projection layer, and connectors - Remove forced `out.float()` in encode_token_weights to prevent downgrading to fp32 after projection - This allows SageAttention's optimized kernel to run instead of falling back to PyTorch attention Fixes the warning: "Error running sage attention: Input tensors must be in dtype of torch.float16 or torch.bfloat16, using pytorch attention instead."
HyperExtendedReality
requested review from
Kosinkadink,
comfyanonymous and
guill
as code owners
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Outdated suggestions cannot be applied.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.
out.float()in encode_token_weights to prevent downgrading to fp32 after projectionFixes the warning:
"Error running sage attention: Input tensors must be in dtype of torch.float16 or torch.bfloat16, using pytorch attention instead."