fix: auto-disable dynamic shapes when custom KV cache is enabled#235
Open
psiddh wants to merge 1 commit into
Open
fix: auto-disable dynamic shapes when custom KV cache is enabled#235psiddh wants to merge 1 commit into
psiddh wants to merge 1 commit into
Conversation
The custom KV cache op (update_cache) only supports single-token inputs, but dynamic shapes enables variable-length prefill. This combination exports successfully but crashes at inference with an opaque error. Auto-set disable_dynamic_shapes=True when use_custom_kv_cache=True, with a warning log so users know the override happened. Co-authored-by: Claude <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The custom KV cache op (update_cache) only supports single-token inputs, but dynamic shapes enables variable-length prefill. This combination exports successfully but crashes at inference with an opaque error.
Auto-set disable_dynamic_shapes=True when use_custom_kv_cache=True, with a warning log so users know the override happened.