wind-all 1a443f2772 add multi_npu_qwen3_dense tutorials (#4543) ...

### What this PR does / why we need it?

This PR adds tutorials for the Qwen3-Dense series models, including the
A2 and A3 series, and provides accuracy validation results.



- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: wind-all <anyuting@h-partners.com>

2025-12-10 16:09:56 +08:00

..

DeepSeek-V3.1.md

Drop torchair (#4814)

2025-12-10 09:20:40 +08:00

DeepSeek-V3.2-Exp.md

Drop torchair (#4814)

2025-12-10 09:20:40 +08:00

index.md

add multi_npu_qwen3_dense tutorials (#4543)

2025-12-10 16:09:56 +08:00

multi_node_kimi.md

Drop torchair (#4814)

2025-12-10 09:20:40 +08:00

multi_node_pd_disaggregation_mooncake.md

[P/D] Add readme for PD separation (#4182)

2025-11-28 15:17:59 +08:00

multi_node_qwen3vl.md

[Docs]fix the configuration conflicts in documentation (#4823)

2025-12-09 15:37:38 +08:00

multi_node_ray.md

[Doc] Update doc (#3836)

2025-10-29 11:03:39 +08:00

multi_node.md

Drop torchair (#4814)

2025-12-10 09:20:40 +08:00

multi_npu_kimi-k2-thinking.md

[Feat] Support native Kimi-K2-Thinking native W4A16 quantized experts weights (#4516)

2025-12-10 15:58:52 +08:00

multi_npu_moge.md

Drop torchair (#4814)

2025-12-10 09:20:40 +08:00

multi_npu_quantization.md

[Info][main] Corrected the errors in the information (#4055)

2025-11-08 18:48:59 +08:00

multi_npu_qwen3_moe.md

[Doc] Update doc (#3836)

2025-10-29 11:03:39 +08:00

multi_npu_qwen3_next.md

Update triton package name (#4563)

2025-11-29 15:00:40 +08:00

multi_npu.md

[Info][main] Corrected the errors in the information (#4055)

2025-11-08 18:48:59 +08:00

Qwen2.5-Omni.md

[Doc] Add single NPU tutorial for Qwen2.5-Omni-7B (#4446)

2025-11-29 11:57:29 +08:00

Qwen3-235B-A22B.md

[Doc] Add Qwen3-235B tutorial (#4358)

2025-12-08 20:06:46 +08:00

Qwen3-Coder-30B-A3B.md

[Doc] Add tutorial for Qwen3-Coder-30B-A3B (#4391)

2025-12-02 16:03:37 +08:00

Qwen3-Dense.md

add multi_npu_qwen3_dense tutorials (#4543)

2025-12-10 16:09:56 +08:00

single_node_300i.md

[Doc] Update doc (#3836)

2025-10-29 11:03:39 +08:00

single_node_pd_disaggregation_mooncake.md

[P/D][main]Offline the llmdatadist connector related parts of the code and files. (#4780)

2025-12-09 22:36:43 +08:00

single_npu_qwen2_audio.md

[Info][main] Corrected the errors in the information (#4055)

2025-11-08 18:48:59 +08:00

single_npu_qwen2.5_vl.md

[Info][main] Correct the mistake in information documents (#4157)

2025-11-13 15:53:58 +08:00

single_npu_qwen3_embedding.md

[Doc] Update doc (#3836)

2025-10-29 11:03:39 +08:00

single_npu_qwen3_quantization.md

[Info][main] Corrected the errors in the information (#4055)

2025-11-08 18:48:59 +08:00

single_npu_qwen3_w4a4.md

[Doc] add qwen3 w4a4 tutorial (#4076)

2025-11-10 20:30:07 +08:00

single_npu.md

[Doc] Fix DeepSeek-3.2-Exp doc, remove v0.11.0rc0 outdated infos. (#4095)

2025-11-12 09:11:31 +08:00