Skip to content

Conversation

@VDV1985
Copy link
Contributor

@VDV1985 VDV1985 commented Nov 19, 2025

Motivation

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

@github-actions github-actions bot added the documentation Improvements or additions to documentation label Nov 19, 2025
@@ -0,0 +1,69 @@
## Examples
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it would be better to change the file name to deepseek-family-examples.md

#### vLLM

vLLM is still a major prerequisite on Ascend NPU. Because of `torch==2.6.0` limitation, only vLLM v0.8.5 is supported.
vLLM is still a major prerequisite on Ascend NPU.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think vLLM is not a major prerequisite on Ascend NPU, but for SGLang

Comment on lines 89 to +114
#### Triton on Ascend
```shell
BISHENG_NAME="Ascend-BiSheng-toolkit_aarch64.run"
BISHENG_URL="https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/sglang/${BISHENG_NAME}"
wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
```
```shell
pip install triton-ascend==3.2.0rc4
```
If you want to install Triton on Ascend nightly build or from sources, follow [installation guide](https://gitcode.com/Ascend/triton-ascend/blob/master/docs/sources/getting-started/installation.md)

_Notice:_ We recommend installing triton-ascend from source due to its rapid development, the version on PYPI can't keep up for know. This problem will be solved on Sep. 2025, afterwards `pip install` would be the one and only installing method.

Please follow Triton-on-Ascend's [installation guide from source](https://gitee.com/ascend/triton-ascend#2%E6%BA%90%E4%BB%A3%E7%A0%81%E5%AE%89%E8%A3%85-triton-ascend) to install the latest `triton-ascend` package.
#### SGLang Kernels NPU
For installation of SGLang Kernels NPU check the [installation guide](https://github.com/sgl-project/sgl-kernel-npu/blob/main/python/sgl_kernel_npu/README.md).

#### DeepEP-compatible Library

We are also providing a DeepEP-compatible Library as a drop-in replacement of deepseek-ai's DeepEP library, check the [installation guide](https://github.com/sgl-project/sgl-kernel-npu/blob/main/python/deep_ep/README.md).

#### CustomOps
_TODO: to be removed once merged into sgl-kernel-npu
```shell
wget https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/ops/CANN-custom_ops-8.2.0.0-$DEVICE_TYPE-linux.aarch64.run
chmod a+x ./CANN-custom_ops-8.2.0.0-$DEVICE_TYPE-linux.aarch64.run
./CANN-custom_ops-8.2.0.0-$DEVICE_TYPE-linux.aarch64.run --quiet --install-path=/usr/local/Ascend/ascend-toolkit/latest/opp
wget https://sglang-ascend.obs.cn-east-3.myhuaweicloud.com/ops/custom_ops-1.0.$DEVICE_TYPE-cp311-cp311-linux_aarch64.whl
pip install ./custom_ops-1.0.$DEVICE_TYPE-cp311-cp311-linux_aarch64.whl
```
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How about using a table to collect these prerequisites? Personally, I think it's a bit long to read


### Running DeepSeek-V3

Running DeepSeek with PD disaggregation on 2 x Atlas 800I A3.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

please add another qwen-family-examples.md

@ping1jing2 ping1jing2 self-assigned this Nov 19, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants