Jade Zheng 38570cfeb6 [Feature] Support kv nz feature for DeepSeek decode node in disagg-prefill scenario (#3072) ...

By converting the KV cache from ND to NZ format when the decode node
receives it, this PR ensures that the KV NZ feature works correctly
during the decoding phase in disagg-prefill scenario.

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
Co-authored-by: ghphotoframe <854746559@qq.com>
Co-authored-by: alex101-ops <alex1015718386@gmail.com>

2025-12-31 14:24:04 +08:00

..

configuration

[Feature] Support kv nz feature for DeepSeek decode node in disagg-prefill scenario (#3072)

2025-12-31 14:24:04 +08:00

deployment_guide

[Doc] Added deploying on k8s with kthena (#4674)

2025-12-23 17:46:04 +08:00

feature_guide

[bugfix][main]KV Pool for KV Transfer in PD Disaggregation Scenarios (#5398)

2025-12-27 09:53:57 +08:00

support_matrix

[doc] Add context parallel user guide (#5358)

2025-12-26 17:03:47 +08:00

release_notes.md

[Doc] Fix issue link for 0.12.0 (#5500)

2025-12-30 10:34:20 +08:00