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

[CI] Upgrade CANN to 8.5.0 (#6070)

Browse Source 
### What this PR does / why we need it?
1. Upgrade CANN to 8.5.0
2. move triton-ascend 3.2.0 to requirements

note: we skipped the two failed e2e test, see
https://github.com/vllm-project/vllm-ascend/issues/6076 for more detail.
We'll fix it soon.


### How was this patch tested?
Closes: https://github.com/vllm-project/vllm-ascend/issues/5494

- vLLM version: v0.13.0
- vLLM main:
d68209402d

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2026-01-22 09:29:50 +08:00
committed by GitHub
parent ab676413e6
commit 69740039b7
30 changed files with 70 additions and 154 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
docs/source/tutorials/DeepSeek-V3.2.md
View File

@@ -32,23 +32,13 @@ If you want to deploy multi-node environment, you need to verify multi-node comm
You can using our official docker image to run `DeepSeek-V3.2` directly..
:::{note}
We strongly recommend you to install triton ascend package to speed up the inference.
The [Triton Ascend](https://gitee.com/ascend/triton-ascend) is for better performance, please follow the instructions below to install it and its dependency.
Install the Ascend BiSheng toolkit, execute the command:
We strongly recommend you to install clang make triton ascend stable enough. For Ubuntu, the command is
```bash
BISHENG_NAME="Ascend-BiSheng-toolkit_$(uname -i)_20260105.run"
BISHENG_URL="https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${BISHENG_NAME}"
wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
export PATH=/usr/local/Ascend/tools/bishengir/bin:$PATH
```
apt-get -y clang-15
Install Triton Ascend:
```bash
python3 -m pip install triton-ascend==3.2.0
update-alternatives --install /usr/bin/clang clang /usr/bin/clang-15 20
update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-15 20
```
:::

18
docs/source/tutorials/Qwen3-Next.md
View File

@@ -53,23 +53,15 @@ docker run --rm \
The Qwen3 Next is using [Triton Ascend](https://gitee.com/ascend/triton-ascend) which is currently experimental. In future versions, there may be behavioral changes related to stability, accuracy, and performance improvement.
### Install Triton Ascend
### Install Clang
The [Triton Ascend](https://gitee.com/ascend/triton-ascend) is required when you run Qwen3 Next, please follow the instructions below to install it and its dependency.
Install the Ascend BiSheng toolkit, execute the command:
We strongly recommend you to install clang make triton ascend stable enough. For Ubuntu, the command is
```bash
BISHENG_NAME="Ascend-BiSheng-toolkit_$(uname -i)_20260105.run"
BISHENG_URL="https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${BISHENG_NAME}"
wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
export PATH=/usr/local/Ascend/tools/bishengir/bin:$PATH
```
apt-get -y clang-15
Install Triton Ascend:
```bash
python3 -m pip install triton-ascend==3.2.0
update-alternatives --install /usr/bin/clang clang /usr/bin/clang-15 20
update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-15 20
```
### Inference