transformers
8010f3cf - feat: add cache retention for requests (#38446)

Commit
215 days ago
feat: add cache retention for requests (#38446) * feat: add cache retention for requests * fix: propagate `manual_eviction` param & refactor `finish_request` `finish_request` now only takes `request_id: str` as an input rather than the full `RequestState`, which was not needed and simplifies calling from `ContinuousBatchingManager::evict_request_from_cache` * refactor: pop req from `active_requests` * Apply style fixes --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Author
Parents
Loading