XiaoxinWang 738bf2b720 support qwen3-next full_decode_only mode. (#3949) ...

### What this PR does / why we need it?
support qwen3-next full_decode_only mode. 
bs=1, max_token=1024
| branch| tps| e2e time|
| --- | --- | --- |
|piecewise  |3.06  | 8.15 |
|fulldecodeonly | 7.2 | 3.47 |

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

Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>

2025-11-05 08:46:05 +08:00

..

test_data_parallel.py

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +08:00

test_expert_parallel.py

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +08:00

test_external_launcher.py

[Test] enable external launcher and add e2e test for sleep mode in level2 (#3344)

2025-10-11 17:29:38 +08:00

test_full_graph_mode.py

fix pagedattention to support fullgraph. (#3436)

2025-10-14 16:10:09 +08:00

test_fused_moe_allgather_ep.py

Refactor e2e CI (#2276)

2025-09-02 09:02:22 +08:00

test_ilama_lora_tp2.py

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +08:00

test_offline_inference_distributed.py

[Perf] move quant before allgather in Allgather EP (#3420)

2025-11-04 16:49:58 +08:00

test_pipeline_parallel.py

[bugfix] fix pipeline parallel for mla & sfa attention backend (#3459)

2025-10-15 17:13:27 +08:00

test_prefix_caching.py

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +08:00

test_qwen3_moe.py

Reapply "[MoE] [Refactor] Remove manual memory cleanup (#3365)" (#3483) (#3512)

2025-10-22 11:41:30 +08:00

test_qwen3_next.py

support qwen3-next full_decode_only mode. (#3949)

2025-11-05 08:46:05 +08:00

test_single_request_aclgraph.py

[Test] Add new test model for aclgraph single_request (#3888)

2025-10-31 11:23:13 +08:00

test_torchair_graph_mode.py

[Test] Add new e2e test use deepseek-v2-lite in ge graph mode (#3937)

2025-11-03 20:10:01 +08:00

test_weight_loader.py

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +08:00