[NPU] chore: bump basic software version to 8.3.rc2 (#14614)

.github/workflows/nightly-test-npu.yml

@@ -23,7 +23,7 @@ jobs:
       matrix:
         part: [0, 1]
     container:
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-a3-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -69,7 +69,7 @@ jobs:
       matrix:
         part: [0]
     container:
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-a3-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -115,7 +115,7 @@ jobs:
       matrix:
         part: [0]
     container:
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-a3-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
     steps:
       - name: Checkout code
         uses: actions/checkout@v4

.github/workflows/pr-test-npu.yml

@@ -45,7 +45,7 @@ jobs:
     if: needs.check-changes.outputs.main_package == 'true'
     runs-on: linux-arm64-npu-1
     container:
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -88,7 +88,7 @@ jobs:
       matrix:
         part: [0, 1, 2]
     container:
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -127,7 +127,7 @@ jobs:
     if: needs.check-changes.outputs.main_package == 'true'
     runs-on: linux-arm64-npu-4
     container:
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -170,7 +170,7 @@ jobs:
       matrix:
         part: [0, 1]
     container:
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-a3-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-a3-ubuntu22.04-py3.11
     steps:
       - name: Checkout code
         uses: actions/checkout@v4

.github/workflows/release-docker-npu-nightly.yml

@@ -19,7 +19,7 @@ jobs:
     runs-on: ubuntu-22.04-arm
     strategy:
       matrix:
-        cann_version: ["8.3.rc1"]
+        cann_version: ["8.3.rc2"]
         device_type: ["910b", "a3"]
     steps:
       - name: Checkout repository
@@ -73,6 +73,6 @@ jobs:
           push: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
           provenance: false
           build-args: |
-            SGLANG_KERNEL_NPU_TAG=20251128
+            SGLANG_KERNEL_NPU_TAG=20251206
             CANN_VERSION=${{ matrix.cann_version }}
             DEVICE_TYPE=${{ matrix.device_type }}

.github/workflows/release-docker-npu.yml

@@ -17,7 +17,7 @@ jobs:
     runs-on: ubuntu-22.04-arm
     strategy:
       matrix:
-        cann_version: ["8.3.rc1"]
+        cann_version: ["8.3.rc2"]
         device_type: ["910b", "a3"]
     steps:
       - name: Checkout repository
@@ -70,6 +70,6 @@ jobs:
           push: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
           provenance: false
           build-args: |
-            SGLANG_KERNEL_NPU_TAG=20251128
+            SGLANG_KERNEL_NPU_TAG=20251206
             CANN_VERSION=${{ matrix.cann_version }}
             DEVICE_TYPE=${{ matrix.device_type }}

docker/npu.Dockerfile

@@ -1,4 +1,4 @@
-ARG CANN_VERSION=8.3.rc1
+ARG CANN_VERSION=8.3.rc2
 ARG DEVICE_TYPE=a3
 ARG OS=ubuntu22.04
 ARG PYTHON_VERSION=py3.11

docs/platforms/ascend_npu.md

@@ -18,7 +18,7 @@ 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 8.3.RC1 or higher, check the [installation guide](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/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 8.3.RC2 or higher, check the [installation guide](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/83RC1/softwareinst/instg/instg_0008.html?Mode=PmIns&InstallType=local&OS=openEuler&Software=cannToolKit)
 
 #### MemFabric Adaptor
 

docs/platforms/ascend_npu_deepseek_example.md

@@ -30,7 +30,7 @@ python3 -m sglang.launch_server \
     --trust-remote-code \
     --attention-backend ascend \
     --device npu \
-    --quantization w8a8_int8 \
+    --quantization modelslim \
     --watchdog-timeout 9000 \
     --host 127.0.0.1 \
     --port 6688 \
@@ -89,7 +89,7 @@ python -m sglang.launch_server \
     --mem-fraction-static 0.6 \
     --attention-backend ascend \
     --device npu \
-    --quantization w8a8_int8 \
+    --quantization modelslim \
     --disaggregation-transfer-backend ascend \
     --max-running-requests 8 \
     --context-length 8192 \
@@ -145,7 +145,7 @@ python -m sglang.launch_server \
     --max-running-requests 352 \
     --attention-backend ascend \
     --device npu \
-    --quantization w8a8_int8 \
+    --quantization modelslim \
     --moe-a2a-backend deepep \
     --enable-dp-attention \
     --deepep-mode low_latency \
@@ -214,7 +214,7 @@ do
       --mem-fraction-static 0.81 \
       --attention-backend ascend \
       --device npu \
-      --quantization w8a8_int8 \
+      --quantization modelslim \
       --disaggregation-transfer-backend ascend \
       --max-running-requests 8 \
       --context-length 8192 \
@@ -275,7 +275,7 @@ do
       --max-running-requests 832 \
       --attention-backend ascend \
       --device npu \
-      --quantization w8a8_int8 \
+      --quantization modelslim \
       --moe-a2a-backend deepep \
       --enable-dp-attention \
       --deepep-mode low_latency \

docs/references/mindspore_models.md

@@ -7,7 +7,7 @@ MindSpore is a high-performance AI framework optimized for Ascend NPUs. This doc
 ## Requirements
 
 MindSpore currently only supports Ascend NPU devices. Users need to first install Ascend CANN software packages.
-The CANN software packages can be downloaded from the [Ascend Official Website](https://www.hiascend.com). The recommended version is 8.3.RC1.
+The CANN software packages can be downloaded from the [Ascend Official Website](https://www.hiascend.com). The recommended version is 8.3.RC2.
 
 ## Supported Models
 

scripts/ci/npu_ci_install_dependency.sh

@@ -49,7 +49,7 @@ wget -O "${BISHENG_NAME}" "${BISHENG_URL}" && chmod a+x "${BISHENG_NAME}" && "./
 
 
 ### Install sgl-kernel-npu
-SGL_KERNEL_NPU_TAG="20251128"
+SGL_KERNEL_NPU_TAG="20251206"
 git clone --depth 1 https://github.com/sgl-project/sgl-kernel-npu.git --branch ${SGL_KERNEL_NPU_TAG}
 (cd sgl-kernel-npu && bash ./build.sh && ${PIP_INSTALL} output/deep_ep*.whl output/sgl_kernel_npu*.whl && cd "$(python3 -m pip show deep-ep | grep -E '^Location:' | awk '{print $2}')" && ln -s deep_ep/deep_ep_cpp*.so)