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).

Signed-off-by: Russell Bryant <rbryant@redhat.com>

Signed-off-by: Wallas Santos <wallashss@ibm.com>

Co-authored-by: Roger Wang <ywang@roblox.com>

Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

Co-authored-by: Jerzy Zagorski <jzagorsk@amazon.com>

Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Andrew Feldman <afeld2012@gmail.com>

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

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

[Hotfix][Core][VLM] Disable chunked prefill by default and prefix caching for multimodal models (#8425)

[MISC] Keep chunked prefill enabled by default with long context when prefix caching is enabled (#8342)

Co-authored-by: Michael Goin <michael@neuralmagic.com>

Co-authored-by: Harsha Bikki <harbikh@amazon.com>

Co-authored-by: Alexander Matveev <alexm@neuralmagic.com>

Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com>

Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>

Co-authored-by: afeldman-nm <156691304+afeldman-nm@users.noreply.github.com>

[Core] Fix tracking of model forward time to the span traces in case of PP>1 (#7440)