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

[Doc]Fix tutorial doc expression (#319)

Browse Source 
Fix tutorial doc expression

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2025-03-13 15:24:05 +08:00
committed by GitHub
parent 59ea23d0d3
commit 41aba1cfc1
3 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/tutorials/multi_npu.md
View File

@@ -30,10 +30,10 @@ docker run --rm \
Setup environment variables: Setup environment variables:
```bash ```bash
# Use Modelscope mirror to speed up model download # Load model from ModelScope to speed up download
export VLLM_USE_MODELSCOPE=True export VLLM_USE_MODELSCOPE=True
# To avoid NPU out of memory, set `max_split_size_mb` to any value lower than you need to allocate for Qwen2.5-7B-Instruct # Set `max_split_size_mb` to reduce memory fragmentation and avoid out of memory
export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256 export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256
``` ```

4
docs/source/tutorials/single_npu.md
View File

@@ -29,10 +29,10 @@ docker run --rm \
Setup environment variables: Setup environment variables:
```bash ```bash
# Use Modelscope mirror to speed up model download # Load model from ModelScope to speed up download
export VLLM_USE_MODELSCOPE=True export VLLM_USE_MODELSCOPE=True
# To avoid NPU out of memory, set `max_split_size_mb` to any value lower than you need to allocate for Qwen2.5-7B-Instruct # Set `max_split_size_mb` to reduce memory fragmentation and avoid out of memory
export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256 export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256
``` ```

4
docs/source/tutorials/single_npu_multimodal.md
View File

@@ -29,10 +29,10 @@ docker run --rm \
Setup environment variables: Setup environment variables:
```bash ```bash
# Use Modelscope mirror to speed up model download # Load model from ModelScope to speed up download
export VLLM_USE_MODELSCOPE=True export VLLM_USE_MODELSCOPE=True
# To avoid NPU out of memory, set `max_split_size_mb` to any value lower than you need to allocate for Qwen2.5-7B-Instruct # Set `max_split_size_mb` to reduce memory fragmentation and avoid out of memory
export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256 export PYTORCH_NPU_ALLOC_CONF=max_split_size_mb:256
``` ```