Chendi.XueandNicolò Lucchesi c9e665852a [NIXL] heterogeneous block_size support (#26759) ...

Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>

2025-11-14 21:51:32 -08:00

..

device_communicators

[BugFix] Fix multi-modal async scheduling race condition (#28706)

2025-11-14 01:11:13 -08:00

ec_transfer

[CI/Build] Fix crash due to removed VLLM_USE_V1 attribute in EPD (#28521)

2025-11-11 23:09:33 -08:00

eplb

[EPLB] Refactor balance_packing to use numpy and optimize GPU-CPU transfers in EPLB (#28369)

2025-11-11 00:19:51 -08:00

kv_transfer

[NIXL] heterogeneous block_size support (#26759)

2025-11-14 21:51:32 -08:00

__init__.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -07:00

communication_op.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

kv_events.py

Fix EventPublisherFactory logic for disabled KV cache events (#27419)

2025-10-24 05:00:01 +00:00

parallel_state.py

[Perf] Move gc.freeze logic from EngineCoreProc to EngineCore for better coverage (#27896)

2025-11-10 15:34:18 -08:00

tpu_distributed_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

utils.py

[Chore] Separate out vllm.utils.network_utils (#27164)

2025-10-19 03:06:32 -07:00