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

[Doc] Add NNAL installation guide and requirements (#5235)

Browse Source 
Fixes #2727

- Add NNAL to the software requirements table with version information
- Add note explaining that prebuilt Docker images include NNAL
- Add warning message for manual installation when encountering
libatb.so errors
- Improve visibility of NNAL installation instructions to prevent
runtime errors

This addresses the issue where users encounter 'libatb.so not found'
errors due to missing NNAL installation in their environment.

### What this PR does / why we need it?

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

### How was this patch tested?

- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: menogrey <1299267905@qq.com>
Signed-off-by: hu-qi <huqi1024@gmail.com>
Co-authored-by: zhangyiming <34808445+menogrey@users.noreply.github.com>
This commit is contained in:
huqi
2026-01-05 19:40:26 +08:00
committed by GitHub
parent ec3563334b
commit 9d8b4c8d9d
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
docs/source/installation.md
View File

@@ -15,6 +15,7 @@ This document describes how to install vllm-ascend manually.
| CANN | == 8.3.RC2 | Required for vllm-ascend and torch-npu | | CANN | == 8.3.RC2 | Required for vllm-ascend and torch-npu |
| torch-npu | == 2.8.0 | Required for vllm-ascend, No need to install manually, it will be auto installed in below steps | | torch-npu | == 2.8.0 | Required for vllm-ascend, No need to install manually, it will be auto installed in below steps |
| torch | == 2.8.0 | Required for torch-npu and vllm | | torch | == 2.8.0 | Required for torch-npu and vllm |
| NNAL | == 8.3.RC2 | Required for libatb.so, enables advanced tensor operations |
There are two installation methods: There are two installation methods:
- **Using pip**: first prepare env manually or via CANN image, then install `vllm-ascend` using pip. - **Using pip**: first prepare env manually or via CANN image, then install `vllm-ascend` using pip.
@@ -45,6 +46,10 @@ Refer to [Ascend Environment Setup Guide](https://ascend.github.io/docs/sources/
The easiest way to prepare your software environment is using CANN image directly: The easiest way to prepare your software environment is using CANN image directly:
```{note}
The CANN prebuilt image includes NNAL (Ascend Neural Network Acceleration Library) which provides libatb.so for advanced tensor operations. No additional installation is required when using the prebuilt image.
```
```{code-block} bash ```{code-block} bash
:substitutions: :substitutions:
# Update DEVICE according to your device (/dev/davinci[0-7]) # Update DEVICE according to your device (/dev/davinci[0-7])
@@ -71,6 +76,10 @@ docker run --rm \
:animate: fade-in-slide-down :animate: fade-in-slide-down
You can also install CANN manually: You can also install CANN manually:
```{warning}
If you encounter "libatb.so not found" errors during runtime, please ensure NNAL is properly installed as shown in the manual installation steps below.
```
```bash ```bash
# Create a virtual environment. # Create a virtual environment.
python -m venv vllm-ascend-env python -m venv vllm-ascend-env