GitLab

Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Abhilash Majumder <abhilash.majumder@intel.com>
Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>

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

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

Co-authored-by: Ruth Evans <ruthevans@Ruths-MacBook-Pro.local>

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).

Signed-off-by: kerthcet <kerthcet@gmail.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

[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

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

[Frontend] [Core] perf: Automatically detect vLLM-tensorized model, update `tensorizer` to version 2.9.0 (#4208)

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

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