GitLab

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>

Co-authored-by: SangBin Cho <sangcho@sangcho-LT93GQWG9C.local>

[Core] replace narrow-usage RayWorkerVllm to general WorkerWrapper to reduce code duplication (#4024)

[WIP][Core][Refactor] move vllm/model_executor/parallel_utils into vllm/distributed and vllm/device_communicators (#3950)

[Misc] [Core] Implement RFC "Augment BaseExecutor interfaces to enable hardware-agnostic speculative decoding" (#3837)