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

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

Browse Source 
1. Add context parallel user guide
2. Add context parallel related message in supported features/models
- vLLM version: release/v0.13.0
- vLLM main:
bc0a5a0c08

Signed-off-by: zhangsicheng5 <zhangsicheng5@huawei.com>
This commit is contained in:
zhangsicheng5
2025-12-26 17:03:47 +08:00
committed by GitHub
parent 09390eaf32
commit 8ed87dfa84
5 changed files with 126 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/source/developer_guide/feature_guide/context_parallel.md
View File

@@ -20,8 +20,7 @@ Its main objective is to eliminate duplicated storage of the KV cache by shardin
DCP primarily influences the Decode logic, as well as the logic for chunked prefill and cached prefill.
## How to Use CP?
<!--TODO(qcs): change cross-reference target to user_guide-->
Please refer to the CP section of the user guide for detailed information: [How to Use CP]
Please refer to the [context parallel user guide](../../user_guide/feature_guide/context_parallel.md) for detailed information.
## How It Works?