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

..

attention

[refactor] refactor model runner capture model (#5230)

2025-12-30 08:32:14 +08:00

compilation

[Feature] Support to use fullgraph with eagle (#5118)

2025-12-29 09:54:51 +08:00

core

Remove ascend schuduler ut (#4684)

2025-12-04 14:10:28 +08:00

device_allocator

add ut for device allocator/camem and mutistream/layers (#2037)

2025-07-31 19:17:27 +08:00

distributed

[Feat] Support MLP_TP feature, exclude MOE layer (#4999)

2025-12-18 20:06:53 +08:00

eplb

[EPLB][refactor] Modification of the initialization logic for expert_map and log2phy（depend on pr5285） (#5311)

2025-12-29 09:26:14 +08:00

fake_weight

[CI] Add unit test framework (#1201)

2025-06-16 18:32:28 +08:00

kv_connector

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

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

model_loader/netloader

Revert "moe_gating_top_k" (#5512)

2025-12-30 15:05:47 +08:00

ops

[EPLB][refactor] Modification of the initialization logic for expert_map and log2phy（depend on pr5285） (#5311)

2025-12-29 09:26:14 +08:00

patch/worker/patch_common

[Refactor] refactor patch module (#3555)

2025-10-21 20:19:46 +08:00

quantization

[quantization] Add w8a16 quantization support (#4541)

2025-12-24 19:49:32 +08:00

sample

[Refactor][Triton] Move reject sample triton kernels into ops/triton (#5324)

2025-12-29 16:15:41 +08:00

spec_decode

[Feature] Refactor PCP &DCP related code (#5214)

2025-12-31 09:29:57 +08:00

worker

[Feature] Refactor PCP &DCP related code (#5214)

2025-12-31 09:29:57 +08:00

__init__.py

[2/4][Refactor] Refactor torchair utils (#1892)

2025-07-21 19:43:30 +08:00

base.py

[Feature]: implement the fusion of allreduce and matmul in prefill phase when tp is enabled (#1926)

2025-07-28 15:13:37 +08:00

conftest.py

[CI] Add Triton Ascend in CI (#4921)

2025-12-23 12:47:35 +08:00

test_ascend_config.py

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

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

test_envs.py

[Misc] Remove redundant imported envs, using envs_ascend instead (#2193)

2025-08-14 09:33:39 +08:00

test_platform.py

Drop 0.12.0 support (#5146)

2025-12-20 09:38:53 +08:00

test_utils.py

[refactor] refactor weight trans nz and transpose (#4878)

2025-12-19 14:27:24 +08:00