[CI]update triton ascend version (#5392)
### 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:
@@ -127,9 +127,11 @@ jobs:
|
||||
if: ${{ inputs.name == 'test_custom_op' }}
|
||||
shell: bash -l {0}
|
||||
run: |
|
||||
. /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
|
||||
wget https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl
|
||||
pip install triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl
|
||||
BISHENG_NAME="Ascend-BiSheng-toolkit_aarch64_20251225.run"
|
||||
BISHENG_URL="https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${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
|
||||
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20251229-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
|
||||
|
||||
- name: Run vllm-project/vllm-ascend test
|
||||
env:
|
||||
|
||||
@@ -108,8 +108,11 @@ jobs:
|
||||
if: ${{ inputs.runner == 'linux-aarch64-a2-4' && contains(inputs.model_list, 'Qwen3-Next-80B-A3B-Instruct') }}
|
||||
shell: bash -l {0}
|
||||
run: |
|
||||
. /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
|
||||
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl"
|
||||
BISHENG_NAME="Ascend-BiSheng-toolkit_aarch64_20251225.run"
|
||||
BISHENG_URL="https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${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
|
||||
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20251229-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
|
||||
|
||||
- name: Install tensorflow (for Molmo-7B-D-0924)
|
||||
if: ${{ inputs.runner == 'linux-aarch64-a2-1' && contains(inputs.model_list, 'Molmo-7B-D-0924') }}
|
||||
|
||||
21
.github/workflows/_e2e_test.yaml
vendored
21
.github/workflows/_e2e_test.yaml
vendored
@@ -80,8 +80,11 @@ jobs:
|
||||
- name: Install Ascend toolkit & triton_ascend
|
||||
shell: bash -l {0}
|
||||
run: |
|
||||
. /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
|
||||
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl"
|
||||
BISHENG_NAME="Ascend-BiSheng-toolkit_aarch64_20251225.run"
|
||||
BISHENG_URL="https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${BISHENG_NAME}"
|
||||
wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
|
||||
source /usr/local/Ascend/8.5.0/bisheng_toolkit/set_env.sh
|
||||
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20251229-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
|
||||
|
||||
- name: Run vllm-project/vllm-ascend test
|
||||
env:
|
||||
@@ -191,8 +194,11 @@ jobs:
|
||||
- name: Install Ascend toolkit & triton_ascend
|
||||
shell: bash -l {0}
|
||||
run: |
|
||||
. /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
|
||||
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl"
|
||||
BISHENG_NAME="Ascend-BiSheng-toolkit_aarch64_20251225.run"
|
||||
BISHENG_URL="https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${BISHENG_NAME}"
|
||||
wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
|
||||
source /usr/local/Ascend/8.5.0/bisheng_toolkit/set_env.sh
|
||||
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20251229-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
|
||||
|
||||
- name: Run vllm-project/vllm-ascend test (light)
|
||||
env:
|
||||
@@ -288,8 +294,11 @@ jobs:
|
||||
- name: Install Ascend toolkit & triton_ascend
|
||||
shell: bash -l {0}
|
||||
run: |
|
||||
. /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
|
||||
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl"
|
||||
BISHENG_NAME="Ascend-BiSheng-toolkit_aarch64_20251225.run"
|
||||
BISHENG_URL="https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${BISHENG_NAME}"
|
||||
wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
|
||||
source /usr/local/Ascend/8.5.0/bisheng_toolkit/set_env.sh
|
||||
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20251229-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
|
||||
|
||||
- name: Run vllm-project/vllm-ascend test for V1 Engine
|
||||
working-directory: ./vllm-ascend
|
||||
|
||||
7
.github/workflows/pr_test_light.yaml
vendored
7
.github/workflows/pr_test_light.yaml
vendored
@@ -130,8 +130,11 @@ jobs:
|
||||
- name: Install Ascend toolkit & triton_ascend
|
||||
shell: bash -l {0}
|
||||
run: |
|
||||
. /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
|
||||
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27_aarch64.whl"
|
||||
BISHENG_NAME="Ascend-BiSheng-toolkit_aarch64_20251225.run"
|
||||
BISHENG_URL="https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${BISHENG_NAME}"
|
||||
wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./${BISHENG_NAME}" --install && rm "${BISHENG_NAME}"
|
||||
source /usr/local/Ascend/8.5.0/bisheng_toolkit/set_env.sh
|
||||
python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20251229-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
|
||||
|
||||
- name: Run unit test
|
||||
env:
|
||||
|
||||
@@ -36,17 +36,20 @@ We strongly recommend you to install triton ascend package to speed up the infer
|
||||
|
||||
The [Triton Ascend](https://gitee.com/ascend/triton-ascend) is for better performance, please follow the instructions below to install it and its dependency.
|
||||
|
||||
Source the Ascend BiSheng toolkit, execute the command:
|
||||
Install the Ascend BiSheng toolkit, execute the command:
|
||||
|
||||
```bash
|
||||
source /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
|
||||
BISHENG_NAME="Ascend-BiSheng-toolkit_$(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
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
@@ -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:
|
||||
|
||||
Reference in New Issue
Block a user