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

..

_cann_ops_custom

[Kernel] add custom op GmmSwigluQuantWeightNzTensorList (#3804)

2025-11-28 18:06:39 +08:00

attention

[Refactor] Provide a framework to accommodate operators for different hardware devices (#5735)

2026-01-13 09:53:26 +08:00

compilation

[bugfix]limit graph replay sync (#5761)

2026-01-12 16:46:21 +08:00

core

[CI] fix lint (#5216)

2025-12-20 17:03:25 +08:00

device

[Refactor] Provide a framework to accommodate operators for different hardware devices (#5735)

2026-01-13 09:53:26 +08:00

device_allocator

[Refactor] Cleanup platform (#5566)

2026-01-07 09:25:55 +08:00

distributed

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

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

eplb

[Bugfix] Revert pr4214 multi-stream collect expert hotpot (#5529)

2026-01-07 11:26:47 +08:00

kv_offload

[BugFix] Fix npu-cpu offloading interface change bug. (#5290)

2025-12-27 10:21:20 +08:00

lora

[BufFix]Fix the error when using Ascend custom operators with rank=128 (#5394)

2026-01-09 15:57:43 +08:00

model_loader

[BugFix] NetLoader: No backend type associated with device type npu (#5700)

2026-01-09 15:54:54 +08:00

ops

[CustomOp][Perf] Merge Q/K split to simplify AscendApplyRotaryEmb for better performance (#5799)

2026-01-13 15:47:23 +08:00

patch

[BugFix][Fusion] Fix graph fusion failure problem (#5676)

2026-01-07 18:42:55 +08:00

quantization

adapt to minimax_m2 (#5624)

2026-01-10 23:01:35 +08:00

sample

[Feature] add the magicmtp speculative decoding acceleration algorithm (#5542)

2026-01-08 09:15:55 +08:00

spec_decode

[BugFix] Support setting tp=1 for the Eagle draft model to take effect (#5519)

2026-01-13 09:14:30 +08:00

worker

[Refactor] Modify the binding logic to allocate CPU cores for each NPU card (#5555)

2026-01-13 09:21:28 +08:00

xlite

[BugFix] Xlite: Bypass the padding of the graph mode in non-MTP cases to obtain the correct decode num. (#5711)

2026-01-09 15:55:30 +08:00

__init__.py

clean up model module (#4611)

2025-12-02 17:35:47 +08:00

ascend_config.py

[CI]Add Disaggregated PD Nightly Test for Qwen3-235B and Qwen3-VL-235B (#5502)

2026-01-09 16:25:20 +08:00

ascend_forward_context.py

enable ep32 for dispatch_ffn_combine (#5787)

2026-01-13 14:35:52 +08:00

batch_invariant.py

[Feature] implement basic framework for batch invariant (#5517)

2026-01-07 09:11:26 +08:00

cpu_binding.py

[Refactor] Modify the binding logic to allocate CPU cores for each NPU card (#5555)

2026-01-13 09:21:28 +08:00

envs.py

enable ep32 for dispatch_ffn_combine (#5787)

2026-01-13 14:35:52 +08:00

flash_common3_context.py

[Perf]enable prefill flashcommon3 (#4065)

2025-12-14 09:34:13 +08:00

meta_registration.py

Fix the bugs about operator registration by PyTorch Dispatcher (#2786)

2025-09-13 11:58:52 +08:00

platform.py

[Feature] Support for cross-attention and whisper model (#5592)

2026-01-11 11:38:45 +08:00

profiling_config.py

Drop ascend scheduler (#4623)

2025-12-05 09:03:45 +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