GitLab

[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)

[Bugfix] Update flashinfer.py with PagedAttention forwards - Fixes Gemma2 OpenAI Server Crash (#6501)

[Kernel] Correctly invoke prefill & decode kernels for cross-attention (towards eventual encoder/decoder model support) (#4888)
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

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

Co-authored-by: LiuXiaoxuanPKU &lt;llilyliupku@gmail.com&gt;, bong-furiosa <bongwon.jang@furiosa.ai>

Signed-off-by: Stephanie Wang <swang@cs.berkeley.edu>
Signed-off-by: Stephanie <swang@anyscale.com>
Co-authored-by: Stephanie <swang@anyscale.com>

[Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode to a single API (#4681)

This PR combines prepare_prompt and prepare_decode into a single API. This PR also coelsce the attn metadata for prefill/decode to a single class and allow to slice them when running attn backend.

It also refactors subquery_start_loc which was not refactored in the previous PR