[NPU] bump sgl-kernel-npu to 2026.02.01.post2 (#19178)

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

@@ -1,5 +1,11 @@
 name: Release Docker Images Nightly (NPU)
 on:
+  pull_request:
+    branches:
+      - 'main'
+    paths:
+      - '.github/workflows/release-docker-npu-nightly.yml'
+      - 'docker/npu.Dockerfile'
   workflow_dispatch:
   schedule:
     - cron: "0 0 * * *"

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

@@ -87,7 +87,7 @@ jobs:
           push: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
           provenance: false
           build-args: |
-            SGLANG_KERNEL_NPU_TAG=2026.01.28
+            SGLANG_KERNEL_NPU_TAG=2026.02.01.post2
             CANN_VERSION=${{ matrix.cann_version }}
             DEVICE_TYPE=${{ matrix.device_type }}
             SGLANG_TAG=${{ steps.version.outputs.version }}

scripts/ci/npu/npu_ci_install_dependency.sh

@@ -44,11 +44,11 @@ ${PIP_INSTALL} triton-ascend
 
 
 ### Install sgl-kernel-npu
-SGLANG_KERNEL_NPU_TAG="2026.01.21"
+SGLANG_KERNEL_NPU_TAG="2026.02.01.post2"
 mkdir sgl-kernel-npu
-(cd sgl-kernel-npu && wget https://github.com/sgl-project/sgl-kernel-npu/releases/download/${SGLANG_KERNEL_NPU_TAG}/sgl-kernel-npu_${SGLANG_KERNEL_NPU_TAG}_8.5.0_${DEVICE_TYPE}.zip \
-&& unzip sgl-kernel-npu_${SGLANG_KERNEL_NPU_TAG}_8.5.0_${DEVICE_TYPE}.zip \
-&& ${PIP_INSTALL} output/deep_ep*.whl output/sgl_kernel_npu*.whl \
+(cd sgl-kernel-npu && wget https://github.com/sgl-project/sgl-kernel-npu/releases/download/${SGLANG_KERNEL_NPU_TAG}/sgl-kernel-npu-${SGLANG_KERNEL_NPU_TAG}-torch2.8.0-py311-cann8.5.0-${DEVICE_TYPE}-$(arch).zip \
+&& unzip ./sgl-kernel-npu-${SGLANG_KERNEL_NPU_TAG}-torch2.8.0-py311-cann8.5.0-${DEVICE_TYPE}-$(arch).zip \
+&& ${PIP_INSTALL} ./deep_ep*.whl ./sgl_kernel_npu*.whl \
 && (cd "$(python3 -m pip show deep-ep | grep -E '^Location:' | awk '{print $2}')" && ln -s deep_ep/deep_ep_cpp*.so))