llama.cpp
server : refactor prompt cache state ownership
#25649
Open

server : refactor prompt cache state ownership #25649

ggerganov wants to merge 3 commits into master from gg/server-clear-checkpoints
ggerganov
ggerganov server : clear checkpoints upon prompt clear
80bef387
ggerganov server : move the prompt state data to the server_prompt_cache
a6fb362e
github-actions github-actions added server
ggerganov server : handle batched slot being cleared
07e604b1
ggerganov ggerganov marked this pull request as ready for review 59 minutes ago
ggerganov ggerganov requested a review 59 minutes ago

Login to write a write a comment.

Login via GitHub

Reviewers
No reviews
Assignees
No one assigned
Labels
Milestone