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

[Doc] Add reinstall instructions doc (#1303)

Browse Source 
Add a new FAQ, if users re-install vllm-ascend with pip, the `build`
folder should be removed first

---------

Signed-off-by: rjg-lyh <1318825571@qq.com>
Signed-off-by: weiguihua <weiguihua2@huawei.com>
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
This commit is contained in:
weiguihua2
2025-06-23 14:06:27 +08:00
committed by GitHub
parent 15592c0d48
commit e1123172d1
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/source/faqs.md
View File

@@ -114,7 +114,7 @@ In scenarios where NPUs have limited HBM (High Bandwidth Memory) capacity, dynam
- **Configure `PYTORCH_NPU_ALLOC_CONF`**: Set this environment variable to optimize NPU memory management. For example, you can `export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True` to enable virtual memory feature to mitigate memory fragmentation caused by frequent dynamic memory size adjustments during runtime, see more note in: [PYTORCH_NPU_ALLOC_CONF](https://www.hiascend.com/document/detail/zh/Pytorch/700/comref/Envvariables/Envir_012.html).
### 15. Failed to enable NPU graph mode when running DeepSeek?
### 16. Failed to enable NPU graph mode when running DeepSeek?
You may encounter the following error if running DeepSeek with NPU graph mode enabled. The allowed number of queries per kv when enabling both MLA and Graph mode only support {32, 64, 128}, **Thus this is not supported for DeepSeek-V2-Lite**, as it only has 16 attention heads. The NPU graph mode support on DeepSeek-V2-Lite will be done in the future.
And if you're using DeepSeek-V3 or DeepSeek-R1, please make sure after the tensor parallel split, num_heads / num_kv_heads in {32, 64, 128}.
@@ -123,3 +123,6 @@ And if you're using DeepSeek-V3 or DeepSeek-R1, please make sure after the tenso
[rank0]: RuntimeError: EZ9999: Inner Error!
[rank0]: EZ9999: [PID: 62938] 2025-05-27-06:52:12.455.807 numHeads / numKvHeads = 8, MLA only support {32, 64, 128}.[FUNC:CheckMlaAttrs][FILE:incre_flash_attention_tiling_check.cc][LINE:1218]
```
### 17. Failed to reinstall vllm-ascend from source after uninstalling vllm-ascend?
You may encounter the problem of C compilation failure when reinstalling vllm-ascend from source using pip. If the installation fails, it is recommended to use `python setup.py install` to install, or use `python setup.py clean` to clear the cache.