EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Doc]Add single node PD disaggregation instructions (#4337)

Browse Source 
### What this PR does / why we need it?
add single node PD disaggregation instructions for Qwen 2.5VL model.

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

### How was this patch tested?


- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

---------

Signed-off-by: mazhixin <mazhixin7@huawei.com>
Signed-off-by: mazhixin000 <mazhixinkorea@163.com>
Co-authored-by: mazhixin <mazhixin7@huawei.com>
This commit is contained in:
mazhixin000
2025-11-22 23:33:07 +08:00
committed by GitHub
parent ea3372fb0c
commit ab51fcea4c
2 changed files with 174 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/source/tutorials/index.md
View File

@@ -9,6 +9,7 @@ single_npu_qwen2_audio
single_npu_qwen3_embedding
single_npu_qwen3_quantization
single_npu_qwen3_w4a4
single_node_pd_disaggregation_llmdatadist
multi_npu_qwen3_next
multi_npu
multi_npu_moge