minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[NPU] Update documentation for software version upgrades (#26731)

Browse Source
This commit is contained in:
Артем Савкин
2026-06-06 15:06:13 +03:00
committed by GitHub
parent 99cf0a4399
commit 9f28512737
6 changed files with 28 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/full-test-npu.yml
+1 -1
View File
@@ -22,7 +22,7 @@ on:
description: 'The a3 running docker image of the test task.' description: 'The a3 running docker image of the test task.'
required: false required: false
type: string type: string
default: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11' default: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:9.0.0-a3-ubuntu22.04-py3.11'
skip_install_flag: skip_install_flag:
description: 'Indicates whether to skip the installation of sglang, defaulting to false.' description: 'Indicates whether to skip the installation of sglang, defaulting to false.'
required: false required: false
.github/workflows/nightly-test-npu.yml
+1 -1
View File
@@ -25,7 +25,7 @@ on:
description: 'The a3 running docker image of the test task.' description: 'The a3 running docker image of the test task.'
required: false required: false
type: string type: string
default: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-a3-ubuntu22.04-py3.11' default: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:9.0.0-a3-ubuntu22.04-py3.11'
skip_install_flag: skip_install_flag:
description: 'Indicates whether to skip the installation of sglang, defaulting to false.' description: 'Indicates whether to skip the installation of sglang, defaulting to false.'
required: false required: false
docker/npu.Dockerfile
+1 -1
View File
@@ -1,4 +1,4 @@
ARG CANN_VERSION=8.5.0 ARG CANN_VERSION=9.0.0
ARG DEVICE_TYPE=a3 ARG DEVICE_TYPE=a3
ARG OS=ubuntu22.04 ARG OS=ubuntu22.04
ARG PYTHON_VERSION=py3.11 ARG PYTHON_VERSION=py3.11
docs_new/docs/hardware-platforms/ascend-npus/ascend_npu.mdx
+21 -16
View File
@@ -20,33 +20,38 @@ You can install SGLang using any of the methods below. Please go through `System
<tbody> <tbody>
<tr> <tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>HDK</td> <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>HDK</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>25.5.2</td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>26.0.RC1</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><a href="https://www.hiascend.com/hardware/firmware-drivers/commercial?product=7&amp;model=33">link</a></td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><a href="https://www.hiascend.com/hardware/firmware-drivers/community?product=1&model=30&cann=9.0.0&driver=Ascend+HDK+26.0.RC1">link</a></td>
</tr> </tr>
<tr> <tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>CANN</td> <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>CANN</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>8.5.0</td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>9.0.0</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><a href="#obtain-cann-image">Obtain Images</a></td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><a href="#obtain-cann-image">Obtain Images</a></td>
</tr> </tr>
<tr> <tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Pytorch Adapter</td> <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Pytorch Adapter</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>7.3.0</td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>26.0.0</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><a href="https://gitcode.com/Ascend/pytorch/releases">link</a></td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><a href="https://gitcode.com/Ascend/pytorch/releases">link</a></td>
</tr> </tr>
<tr> <tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>MemFabric</td> <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>MemFabric</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>1.0.5</td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>1.0.8</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`pip install memfabric-hybrid==1.0.5`</td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`pip install memfabric-hybrid==1.0.8`</td>
</tr> </tr>
<tr> <tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Triton</td> <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Triton</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>3.2.0</td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>3.2.1</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`pip install triton-ascend`</td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><a href="https://gitcode.com/Ascend/triton-ascend/releases/v3.2.1">link</a></td>
</tr> </tr>
<tr> <tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>SGLang NPU Kernel</td> <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>SGLang NPU Kernel</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>NA</td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>2026.05.01.post3</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><a href="https://github.com/sgl-project/sgl-kernel-npu/releases">link</a></td> <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}><a href="https://github.com/sgl-project/sgl-kernel-npu/releases/tag/2026.05.01.post3">link</a></td>
</tr>
<tr>
<td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>MemFabric-zbal</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>1.1.1</td>
<td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>`pip install memfabric-zbal==1.1.1`</td>
</tr> </tr>
</tbody> </tbody>
</table> </table>
@@ -63,14 +68,14 @@ You can obtain the dependency of a specified version of CANN through an image.
<Tab title="Atlas 800I A3"> <Tab title="Atlas 800I A3">
```bash Command ```bash Command
docker pull quay.io/ascend/cann:8.5.0-a3-ubuntu22.04-py3.11 docker pull quay.io/ascend/cann:9.0.0-a3-ubuntu22.04-py3.11
``` ```
</Tab> </Tab>
<Tab title="Atlas 800I A2"> <Tab title="Atlas 800I A2">
```bash Command ```bash Command
docker pull quay.io/ascend/cann:8.5.0-910b-ubuntu22.04-py3.11 docker pull quay.io/ascend/cann:9.0.0-910b-ubuntu22.04-py3.11
``` ```
</Tab> </Tab>
@@ -111,7 +116,7 @@ conda activate sglang_npu
#### CANN #### CANN
Prior to start work with SGLang on Ascend you need to install CANN Toolkit, Kernels operator package and NNAL version 8.5.0, check the [installation guide](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/850/softwareinst/instg/instg_0008.html?Mode=PmIns&InstallType=local&OS=openEuler&Software=cannToolKit) Prior to start work with SGLang on Ascend you need to install CANN Toolkit, Kernels operator package and NNAL version 9.0.0, check the [installation guide](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/900/softwareinst/instg/instg_0008.html?OS=openEuler&InstallType=local)
#### MemFabric-Hybrid #### MemFabric-Hybrid
@@ -180,7 +185,7 @@ Ensure sufficient disk space before pulling images. Each Docker image requires a
1. Download SGLang image 1. Download SGLang image
<Tip> <Tip>
We publish both **stable releases** and **daily builds**. Choose a stable release tag (e.g., `v0.5.10-npu.rc1-a3`) if you prefer a validated version, or a daily build tag (e.g., `main-cann8.5.0-a3`) if you need the latest development changes. We publish both **stable releases** and **daily builds**. Choose a stable release tag (e.g., `v0.5.10-npu.rc1-a3`) if you prefer a validated version, or a daily build tag (e.g., `main-cann9.0.0-a3`) if you need the latest development changes.
</Tip> </Tip>
<Tabs> <Tabs>
@@ -191,7 +196,7 @@ We publish both **stable releases** and **daily builds**. Choose a stable releas
docker pull quay.io/ascend/sglang:v0.5.10-npu.rc1-a3 docker pull quay.io/ascend/sglang:v0.5.10-npu.rc1-a3
# Daily build # Daily build
docker pull quay.io/ascend/sglang:main-cann8.5.0-a3 docker pull quay.io/ascend/sglang:main-cann9.0.0-a3
``` ```
</Tab> </Tab>
@@ -202,7 +207,7 @@ docker pull quay.io/ascend/sglang:main-cann8.5.0-a3
docker pull quay.io/ascend/sglang:v0.5.10-npu.rc1-910b docker pull quay.io/ascend/sglang:v0.5.10-npu.rc1-910b
# Daily build # Daily build
docker pull quay.io/ascend/sglang:main-cann8.5.0-910b docker pull quay.io/ascend/sglang:main-cann9.0.0-910b
``` ```
</Tab> </Tab>
docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx
-2
View File
@@ -1204,7 +1204,6 @@ export SGLANG_SET_CPU_AFFINITY=1
unset ASCEND_LAUNCH_BLOCKING unset ASCEND_LAUNCH_BLOCKING
source /usr/local/Ascend/ascend-toolkit/set_env.sh source /usr/local/Ascend/ascend-toolkit/set_env.sh
source /usr/local/Ascend/nnal/atb/set_env.sh source /usr/local/Ascend/nnal/atb/set_env.sh
export PATH=/usr/local/Ascend/8.5.0/compiler/bishengir/bin:$PATH
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export STREAMS_PER_DEVICE=32 export STREAMS_PER_DEVICE=32
export ASCEND_MF_STORE_URL="tcp://your prefill ip1:24669" export ASCEND_MF_STORE_URL="tcp://your prefill ip1:24669"
@@ -2732,7 +2731,6 @@ unset ASCEND_LAUNCH_BLOCKING
source /usr/local/Ascend/ascend-toolkit/set_env.sh source /usr/local/Ascend/ascend-toolkit/set_env.sh
source /usr/local/Ascend/nnal/atb/set_env.sh source /usr/local/Ascend/nnal/atb/set_env.sh
source /usr/local/Ascend/ascend-toolkit/latest/opp/vendors/customize/bin/set_env.bash source /usr/local/Ascend/ascend-toolkit/latest/opp/vendors/customize/bin/set_env.bash
export PATH=/usr/local/Ascend/8.5.0/compiler/bishengir/bin:$PATH
MODEL_PATH=xxx MODEL_PATH=xxx
docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start.mdx
+4 -4
View File
@@ -18,7 +18,7 @@ Ensure sufficient disk space before proceeding. The Docker image requires at lea
</Warning> </Warning>
<Tip> <Tip>
We publish both **stable releases** and **daily builds**. Choose a stable release tag (e.g., `v0.5.10-npu.rc1-a3`) if you prefer a validated version, or a daily build tag (e.g., `main-cann8.5.0-a3`) if you need the latest development changes. We publish both **stable releases** and **daily builds**. Choose a stable release tag (e.g., `v0.5.10-npu.rc1-a3`) if you prefer a validated version, or a daily build tag (e.g., `main-cann9.0.0-a3`) if you need the latest development changes.
</Tip> </Tip>
<Tabs> <Tabs>
@@ -29,7 +29,7 @@ We publish both **stable releases** and **daily builds**. Choose a stable releas
export IMAGE=quay.io/ascend/sglang:v0.5.10-npu.rc1-a3 export IMAGE=quay.io/ascend/sglang:v0.5.10-npu.rc1-a3
# Daily build # Daily build
export IMAGE=quay.io/ascend/sglang:main-cann8.5.0-a3 export IMAGE=quay.io/ascend/sglang:main-cann9.0.0-a3
docker run -it --rm --privileged --network=host --ipc=host --shm-size=16g \ docker run -it --rm --privileged --network=host --ipc=host --shm-size=16g \
--device=/dev/davinci0 --device=/dev/davinci1 --device=/dev/davinci2 --device=/dev/davinci3 \ --device=/dev/davinci0 --device=/dev/davinci1 --device=/dev/davinci2 --device=/dev/davinci3 \
@@ -53,10 +53,10 @@ docker run -it --rm --privileged --network=host --ipc=host --shm-size=16g \
```shell Command ```shell Command
# Stable release # Stable release
export IMAGE=quay.io/ascend/sglang:v0.5.10-npu.rc1-910b export IMAGE=quay.io/ascend/sglang:v0.5.12-cann8.5.0-910b
# Daily build # Daily build
export IMAGE=quay.io/ascend/sglang:main-cann8.5.0-910b export IMAGE=quay.io/ascend/sglang:main-cann9.0.0-910b
docker run -it --rm --privileged --network=host --ipc=host --shm-size=16g \ docker run -it --rm --privileged --network=host --ipc=host --shm-size=16g \
--device=/dev/davinci0 --device=/dev/davinci1 --device=/dev/davinci2 --device=/dev/davinci3 \ --device=/dev/davinci0 --device=/dev/davinci1 --device=/dev/davinci2 --device=/dev/davinci3 \