fix: handle zero-token KV cache expansion#504
Open
livepeer-robot wants to merge 1 commit intodaydreamlive:mainfrom
Open
fix: handle zero-token KV cache expansion#504livepeer-robot wants to merge 1 commit intodaydreamlive:mainfrom
livepeer-robot wants to merge 1 commit intodaydreamlive:mainfrom
Conversation
Add guard clauses to skip processing when the token/frame count is zero, preventing tensor dimension mismatches during KV cache expansion (e.g. 'expanded size (0) must match existing size'). Guards added in: - DenoiseBlock: skip denoising loop when num_frames == 0 - CleanKVCacheBlock: skip cache cleaning when num_frames == 0 - RecacheFramesBlock: skip recaching when num_recache_frames == 0 - causal_rope_apply: pass through when seq_len == 0 Fixes daydreamlive#500
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add guard clauses to skip processing when the token/frame count is zero, preventing tensor dimension mismatches during KV cache expansion (e.g.
expanded size (0) must match existing size).Guards added in:
DenoiseBlock: skip denoising loop whennum_frames == 0CleanKVCacheBlock: skip cache cleaning whennum_frames == 0RecacheFramesBlock: skip recaching whennum_recache_frames == 0causal_rope_apply: pass through whenseq_len == 0Fixes #500