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

[Doc] add faqs:install vllm-ascend will overwrite existing torch-npu (#3245)

Browse Source 
### What this PR does / why we need it?
add faqs:install vllm-ascend will overwrite existing torch-npu

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.10.2
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.0

Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
This commit is contained in:
weiguihua2
2025-09-29 12:02:23 +08:00
committed by GitHub
parent 373f84a193
commit 065486820b
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/source/faqs.md
View File

@@ -211,3 +211,6 @@ Recommended mitigation strategies:
Root cause analysis: Root cause analysis:
The current stream requirement calculation for size captures only accounts for measurable factors including: data parallel size, tensor parallel size, expert parallel configuration, piece graph count, multistream overlap shared expert settings, and HCCL communication mode (AIV/AICPU). However, numerous unquantifiable elements - such as operator characteristics and specific hardware features - consume additional streams outside of this calculation framework, resulting in stream resource exhaustion during size capture operations. The current stream requirement calculation for size captures only accounts for measurable factors including: data parallel size, tensor parallel size, expert parallel configuration, piece graph count, multistream overlap shared expert settings, and HCCL communication mode (AIV/AICPU). However, numerous unquantifiable elements - such as operator characteristics and specific hardware features - consume additional streams outside of this calculation framework, resulting in stream resource exhaustion during size capture operations.
### 21. Installing vllm-ascend will overwrite the existing torch-npu package？
Installing vllm-ascend will overwrite the existing torch-npu package. If you need to install a specific version of torch-npu, you can manually install the specified version of torch-npu after installing vllm-ascend.