Minor refactoring, resolve conflicts with main #4
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
Co-authored-by: ElizaWszola <[email protected]> Co-authored-by: Michael Goin <[email protected]>
… caching benchmark (vllm-project#3158)
Co-authored-by: Roger Wang <[email protected]>
…ect#3175) Co-authored-by: zixiao <[email protected]>
…on (vllm-project#3176) Co-authored-by: guofangze <[email protected]>
Co-authored-by: Avnish Narayan <[email protected]>
Co-authored-by: Zhuohan Li <[email protected]>
…llm-project#2992) Co-authored-by: Roger Wang <[email protected]>
…lm-project#3123) Co-authored-by: lcskrishna <[email protected]>
) Co-authored-by: Antoni Baum <[email protected]>
…ts. (vllm-project#3181) Co-authored-by: Zhuohan Li <[email protected]>
…ect#2762) and multi-LoRA support (vllm-project#1804) (vllm-project#3263)
…m-project#3551) Co-authored-by: Roy <[email protected]> Co-authored-by: Roger Meier <[email protected]>
…ompt_lens is treated as a list in T5
…oder mode; removed encoder/decoder argument of Sequence
…on of relative position encoding based on packed-variable-length-sequences
…ct T5 inference result. Nothing is broken by this commit, unless there is a subsequent commit with changes in order to pass regression tests.
…ks wrong though. Added not_causal option for attn_bias to kernel interface contracts; also switched to batch size 1 to avoid incorrectness likely caused by packed-variable-sequence-length mask having zeroes rather than -inf's
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Outdated suggestions cannot be applied.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.
No description provided.