zxr2333 78b554dda9 [P/D] layerwise connector supports DeepSeek-V3.2 sparse attention && Distribute transfer tasks to redundant kv_head cards (#5722) ...

### What this PR does / why we need it?
Add new function to mooncake layerwise connector, including:
1. supports sparse attention, for DeepSeek-V3.2
2. Distribute transfer tasks to redundant kv_head cards

This PR is related to [[RFC]: CDCP Scheduling for Disaggregated
Prefilling with KV Cache Layerwise Push
Support](https://github.com/vllm-project/vllm-ascend/issues/4842)

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
By CI.

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

---------

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
Signed-off-by: liziyu <liziyu16@huawei.com>
Co-authored-by: liziyu <liziyu16@huawei.com>

2026-01-10 23:04:16 +08:00

..

e2e

[Feat] flashcomm2+oshard Generalized (#4723)

2026-01-10 22:57:57 +08:00

ut

[P/D] layerwise connector supports DeepSeek-V3.2 sparse attention && Distribute transfer tasks to redundant kv_head cards (#5722)

2026-01-10 23:04:16 +08:00

__init__.py

[SpecDecode] Add spec decode support (#500)

2025-04-17 20:16:32 +08:00