GitLab

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

Co-authored-by: mulin.lyh <mulin.lyh@taobao.com>

Co-authored-by: rsnm2 <rshaw@neuralmagic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>

The 2nd PR for #4532.

This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).

Currently we need to call rotary embedding kernel for each LoRA, which makes it hard to serve multiple long context length LoRA. Add batched rotary embedding kernel and pipe it through.

It replaces the rotary embedding layer to the one that is aware of multiple cos-sin-cache per scaling factors.

Follow up of https://github.com/vllm-project/vllm/pull/3095/files

[Build/CI] Extending the set of AMD tests with Regression, Basic Correctness, Distributed, Engine, Llava Tests (#4797)

Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>

Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

Co-authored-by: SAHIL SUNEJA <suneja@us.ibm.com>

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

Co-authored-by: LiuXiaoxuanPKU <llilyliupku@gmail.com>

Co-authored-by: Lei Wen <wenlei03@qiyi.com>

[Bugfix] Fix the fp8 kv_cache check error that occurs when failing to obtain the CUDA version. (#4173)
Signed-off-by: AnyISalIn <anyisalin@gmail.com>

Co-authored-by: alexm <alexm@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>

Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>

Co-authored-by: Danny Guinther <dguinther@neuralmagic.com>

Co-authored-by: Yun Ding <yunding@nvidia.com>
Co-authored-by: Roger Wang <ywang@roblox.com>

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