Skip to content

Commit 4c769bd

Browse files
weiguihua2rjg-lyh
authored andcommitted
[Doc] Add reinstall instructions doc
Signed-off-by: rjg-lyh <[email protected]>
1 parent ebb2a70 commit 4c769bd

File tree

1 file changed

+9
-1
lines changed

1 file changed

+9
-1
lines changed

docs/source/faqs.md

Lines changed: 9 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -114,7 +114,7 @@ In scenarios where NPUs have limited HBM (High Bandwidth Memory) capacity, dynam
114114

115115
- **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).
116116

117-
### 15. Failed to enable NPU graph mode when running DeepSeek?
117+
### 16. Failed to enable NPU graph mode when running DeepSeek?
118118
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.
119119

120120
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 +123,11 @@ And if you're using DeepSeek-V3 or DeepSeek-R1, please make sure after the tenso
123123
[rank0]: RuntimeError: EZ9999: Inner Error!
124124
[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]
125125
```
126+
127+
### 17. Failed to reinstall vllm-ascend from source after uninstalling vllm-ascend?
128+
If you reinstall vllm-ascend from source after uninstalling vllm-ascend, you need to delete the build directory first, and then resinstall:
129+
130+
```bash
131+
cd vllm-ascend
132+
rm -rf build
133+
```

0 commit comments

Comments
 (0)