zxr2333 46a1614387 [P/D] Improve the performance of Layerwise Connector (#5303) ...

### What this PR does / why we need it?
Improve the performance of Layerwise Connector, mainly includes the
following points:
1. Use event synchronize to replace stream synchronize.
2. Access metaserver when scheduling.
3. Transfer kvcache each Chunk prefill segmentation.

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

### How was this patch tested?
By CI.
- vLLM version: release/v0.13.0
- vLLM main:
5fbfa8d9ef

---------

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

2025-12-31 15:09:01 +08:00

..

test_mooncake_connector.py

[feature] mooncake support pcp/dcp in common conditions (#5224)

2025-12-31 09:53:03 +08:00

test_mooncake_layerwise_connector.py

[P/D] Improve the performance of Layerwise Connector (#5303)

2025-12-31 15:09:01 +08:00

test_remote_decode_lifecycle.py

[Quickfix] update CachedRequestState as NewRequestData changed (#2367)

2025-08-15 07:35:27 +08:00

test_remote_prefill_lifecycle.py

Fix some ci issue and refactor modelrunner (#2445)

2025-08-20 09:01:04 +08:00

utils.py

[Doc][P/D] Fix MooncakeConnector's name (#5172)

2025-12-18 22:29:19 +08:00