liziyu eed9e366a7 [Bugfix][P/D] fix layerwise connector for decoder tp size > num kv heads (#5846) ...

### What this PR does / why we need it?
Fix layerwise connector for decoder tp size > num kv heads. In this case
prefiller should push kv cache to all decoder npu.

- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef

Signed-off-by: liziyu <liziyu16@huawei.com>

2026-01-13 17:30:33 +08:00

..

cpu_offload_manager

[bugfix] adapt to new implemented get_kv_cache_spec in cpuoffload connector (#4311)

2026-01-08 09:15:09 +08:00

device_communicators

[MISC] Clean up torch_npu (#688)

2025-04-29 18:03:38 +08:00

kvpool

[bugfix] A2 Environment Pooling for Memcache Compatibility (#5601)

2026-01-13 09:07:38 +08:00

__init__.py

[Core][Worker] Add UCMConnector for KV Cache Offloading (#4411)

2025-12-16 10:53:30 +08:00

communicator.py

[2/N][Feat] Add MC2 communication method for MoE layers (#2469)

2025-08-26 19:05:23 +08:00

cpu_offload_connector.py

[bugfix] adapt to new implemented get_kv_cache_spec in cpuoffload connector (#4311)

2026-01-08 09:15:09 +08:00

mooncake_connector.py

[P/D][bugfix]Fix the PCP port mapping error issue (#5706)

2026-01-10 22:43:52 +08:00

mooncake_layerwise_connector.py

[Bugfix][P/D] fix layerwise connector for decoder tp size > num kv heads (#5846)

2026-01-13 17:30:33 +08:00

mooncake_transfer_engine.py

[Feature][main]reconstruction kvpool connector to ascend connector (#4438)

2025-11-28 18:08:37 +08:00

parallel_state.py

[refactor] Refactor the interface for shard weight and remove the flashcomm2 o_shared interface. (#5181)

2026-01-08 09:05:02 +08:00

ucm_connector.py

[Bugfix]Add register_kv_cache in ucm_connector (#5657)

2026-01-07 11:30:33 +08:00

utils.py

[Perf] Supports compute-communication overlap in the forward of sfa_v1 in the Sharded-CP feature. (#5701)

2026-01-11 09:47:27 +08:00