GitLab

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

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

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Signed-off-by: lucast2021 <lucast2021@headroyce.org>
Co-authored-by: lucast2021 <lucast2021@headroyce.org>

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Signed-off-by: Umesh Deshpande <udeshpa@us.ibm.com>
Co-authored-by: Umesh Deshpande <udeshpa@us.ibm.com>

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Signed-off-by: Aaron Pham <contact@aarnphm.xyz>

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

Co-authored-by: Jacob Schein <jacobschein@Jacobs-MacBook-Pro-2.local>

Co-authored-by: Swapnil Parekh <swapnilp@ibm.com>
Co-authored-by: Joe G <joseph.granados@h2o.ai>
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>

Co-authored-by: sang <sangcho@anyscale.com>

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

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

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

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

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