GitLab

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

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

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

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

[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

Lora 3 & 4 test seems to have illegal memory access failure after this commit;

[2024-05-14 23:51:18,182 E 22 22] logging.cc:101: Unhandled exception: N3c105ErrorE. what(): CUDA error: an illegal memory access was encountered
<br class="Apple-interchange-newline">
Exmaple: https://buildkite.com/vllm/ci/builds/7382#018f793d-1527-4e1c-ab59-c3a34ec55241

This reverts commit 1356df53.

FILL IN THE PR DESCRIPTION HERE

FIX #xxxx (link existing issues this PR will resolve)

Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>

[Core][Distributed] refactor pynccl to hold multiple communicators (#4591)

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

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

[Core] add an option to log every function call to for debugging hang/crash in distributed inference (#4079)
Co-authored-by: Simon Mo <simon.mo@hey.com>