GitLab

Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>

Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>

Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

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

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

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: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: ZX <zx@lbx.dev>

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

Signed-off-by: Joe Runde <joe@joerun.de>

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

Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>

[Core][Distributed] add coordinator to reduce code duplication in tp and pp (#5293)

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