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

[CI]update triton ascend version (#5392)

Browse Source 
### What this PR does / why we need it?
update triton-ascend version to 1229 and bisheng version in 1225;

- vLLM version: release/v0.13.0
- vLLM main:
254f6b9867
---------
Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com>
This commit is contained in:
meihanc
2025-12-30 09:51:45 +08:00
committed by GitHub
parent 45c3c279e2
commit 8c4e9bb76b
6 changed files with 44 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
docs/source/tutorials/DeepSeek-V3.2.md
View File

@@ -36,17 +36,20 @@ We strongly recommend you to install triton ascend package to speed up the infer
The [Triton Ascend](https://gitee.com/ascend/triton-ascend) is for better performance, please follow the instructions below to install it and its dependency.
Source the Ascend BiSheng toolkit, execute the command:
Install the Ascend BiSheng toolkit, execute the command:
```bash
source /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
BISHENG_NAME="Ascend-BiSheng-toolkit_$(uname -i)_20251225.run"
BISHENG_URL="https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${BISHENG_NAME}"
wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
source /usr/local/Ascend/8.5.0/bisheng_toolkit/set_env.sh
```
Install Triton Ascend:
```bash
wget https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl
pip install triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl
wget https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20251229-cp311-cp311-manylinux_2_27_$(uname -i).manylinux_2_28_$(uname -i).whl
pip install triton_ascend-3.2.0.dev20251229-cp311-cp311-manylinux_2_27_$(uname -i).manylinux_2_28_$(uname -i).whl
```
:::

23
docs/source/tutorials/Qwen3-Next.md
View File

@@ -52,33 +52,24 @@ The Qwen3 Next is using [Triton Ascend](https://gitee.com/ascend/triton-ascend)
### Install Triton Ascend
:::::{tab-set}
::::{tab-item} Linux (AArch64)
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.
Source the Ascend BiSheng toolkit, execute the command:
Install the Ascend BiSheng toolkit, execute the command:
```bash
source /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
BISHENG_NAME="Ascend-BiSheng-toolkit_$(uname -i)_20251225.run"
BISHENG_URL="https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${BISHENG_NAME}"
wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
source /usr/local/Ascend/8.5.0/bisheng_toolkit/set_env.sh
```
Install Triton Ascend:
```bash
wget https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl
pip install triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl
wget https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20251229-cp311-cp311-manylinux_2_27_$(uname -i).manylinux_2_28_$(uname -i).whl
pip install triton_ascend-3.2.0.dev20251229-cp311-cp311-manylinux_2_27_$(uname -i).manylinux_2_28_$(uname -i).whl
```
::::
::::{tab-item} Linux (x86_64)
Coming soon ...
::::
:::::
### Inference
Please make sure you have already executed the command: