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: Varun Sundar Rabindranath <varun@neuralmagic.com>

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

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>

Co-authored-by: Yan Ma <yan.ma@intel.com>

[Bugfix] Ensure multistep lookahead allocation is compatible with cuda graph max capture (#8340)

[Core][Kernels] Enable FP8 KV Cache with Flashinfer backend.  + BugFix for kv_cache_dtype=auto (#7985)
Co-authored-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>

Co-authored-by: Simon Mo <simon.mo@hey.com>

[BUG] fix crash on flashinfer backend with cudagraph disabled, when attention group_size not in [1,2,4,8] (#7509)