diff --git a/.github/workflows/full-test-npu.yml b/.github/workflows/full-test-npu.yml index e57664a3d..42360ff67 100644 --- a/.github/workflows/full-test-npu.yml +++ b/.github/workflows/full-test-npu.yml @@ -22,7 +22,7 @@ on: description: 'The a3 running docker image of the test task.' required: false 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: description: 'Indicates whether to skip the installation of sglang, defaulting to false.' required: false diff --git a/.github/workflows/nightly-test-npu.yml b/.github/workflows/nightly-test-npu.yml index 0ca0e9ae7..3ade42b0b 100644 --- a/.github/workflows/nightly-test-npu.yml +++ b/.github/workflows/nightly-test-npu.yml @@ -25,7 +25,7 @@ on: description: 'The a3 running docker image of the test task.' required: false 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: description: 'Indicates whether to skip the installation of sglang, defaulting to false.' required: false diff --git a/docker/npu.Dockerfile b/docker/npu.Dockerfile index c0dfc55f9..3755edcf8 100644 --- a/docker/npu.Dockerfile +++ b/docker/npu.Dockerfile @@ -1,4 +1,4 @@ -ARG CANN_VERSION=8.5.0 +ARG CANN_VERSION=9.0.0 ARG DEVICE_TYPE=a3 ARG OS=ubuntu22.04 ARG PYTHON_VERSION=py3.11 diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu.mdx index 2bf321d37..7fe4750b1 100644 --- a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu.mdx +++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu.mdx @@ -20,33 +20,38 @@ You can install SGLang using any of the methods below. Please go through `System HDK - 25.5.2 - link + 26.0.RC1 + link CANN - 8.5.0 + 9.0.0 Obtain Images Pytorch Adapter - 7.3.0 + 26.0.0 link MemFabric - 1.0.5 - `pip install memfabric-hybrid==1.0.5` + 1.0.8 + `pip install memfabric-hybrid==1.0.8` Triton - 3.2.0 - `pip install triton-ascend` + 3.2.1 + link SGLang NPU Kernel - NA - link + 2026.05.01.post3 + link + + + MemFabric-zbal + 1.1.1 + `pip install memfabric-zbal==1.1.1` @@ -63,14 +68,14 @@ You can obtain the dependency of a specified version of CANN through an image. ```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 ``` ```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 ``` @@ -111,7 +116,7 @@ conda activate sglang_npu #### 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 @@ -180,7 +185,7 @@ Ensure sufficient disk space before pulling images. Each Docker image requires a 1. Download SGLang image -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. @@ -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 # Daily build -docker pull quay.io/ascend/sglang:main-cann8.5.0-a3 +docker pull quay.io/ascend/sglang:main-cann9.0.0-a3 ``` @@ -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 # Daily build -docker pull quay.io/ascend/sglang:main-cann8.5.0-910b +docker pull quay.io/ascend/sglang:main-cann9.0.0-910b ``` diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx index 0766757b8..d87cd5b10 100644 --- a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx +++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_best_practice.mdx @@ -1204,7 +1204,6 @@ export SGLANG_SET_CPU_AFFINITY=1 unset ASCEND_LAUNCH_BLOCKING source /usr/local/Ascend/ascend-toolkit/set_env.sh source /usr/local/Ascend/nnal/atb/set_env.sh -export PATH=/usr/local/Ascend/8.5.0/compiler/bishengir/bin:$PATH export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True export STREAMS_PER_DEVICE=32 export ASCEND_MF_STORE_URL="tcp://your prefill ip1:24669" @@ -2732,7 +2731,6 @@ unset ASCEND_LAUNCH_BLOCKING source /usr/local/Ascend/ascend-toolkit/set_env.sh source /usr/local/Ascend/nnal/atb/set_env.sh source /usr/local/Ascend/ascend-toolkit/latest/opp/vendors/customize/bin/set_env.bash -export PATH=/usr/local/Ascend/8.5.0/compiler/bishengir/bin:$PATH MODEL_PATH=xxx diff --git a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start.mdx b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start.mdx index 7bd688634..e7dcfbd4c 100644 --- a/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start.mdx +++ b/docs_new/docs/hardware-platforms/ascend-npus/ascend_npu_quick_start.mdx @@ -18,7 +18,7 @@ Ensure sufficient disk space before proceeding. The Docker image requires at lea -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. @@ -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 # 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 \ --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 # 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 -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 \ --device=/dev/davinci0 --device=/dev/davinci1 --device=/dev/davinci2 --device=/dev/davinci3 \