GitLab

Removing the block manager v1. This is the initial piece of prefix-caching-centric design. In order to achieve prefix-caching-centric design, we need to simplify the code path so that we only use v2 block manager (which has much higher performance on prefix caching).

Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>

Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>

[Core] Cross-attention KV caching and memory-management (towards eventual encoder/decoder model support) (#4837)

Co-authored-by: Ruth Evans <ruthevans@Ruths-MacBook-Pro.local>

Co-authored-by: Cade Daniel <edacih@gmail.com>

Co-authored-by: Lei Wen <wenlei03@qiyi.com>
Co-authored-by: Sage Moore <sagemoore@utexas.edu>