[V1][Kernel] Refactor the prefix_prefill kernel so that the caller no longer has to pass in the context lengths#13095

Open

SageMoore wants to merge 4 commits intovllm-project:mainfrom neuralmagic:sage/prefix-prefill-refactor

+12-19

Commits on Feb 10, 2025

init
SageMoore
committed

Commits on Feb 11, 2025

init
SageMoore
committed
minor fix
SageMoore
committed

Commits on Feb 12, 2025

Merge branch 'main' of https://github.com/neuralmagic/vllm into sage/prefix-prefill-refactor
SageMoore
committed