LLM inference in C/C++
C++ ggml
ci: update device matrix for Snapdragon jobs by removing SM8750 (#30620)
Zack Li6420cf5dd588
diff --git a/.github/workflows/build-and-test-snapdragon.yml b/.github/workflows/build-and-test-snapdragon.ymlindex d6420b65f1..29be95c8be 100644--- a/.github/workflows/build-and-test-snapdragon.yml+++ b/.github/workflows/build-and-test-snapdragon.yml@@ -104,11 +104,11 @@ jobs:name: Test on QDC Device (${{ matrix.device }})needs: [android-ndk-snapdragon, linux-iot-snapdragon]runs-on: ubuntu-24.04-arm- timeout-minutes: 90+ timeout-minutes: 180strategy:fail-fast: falsematrix:- device: [SM8750, SM8850, QCS9075M]+ device: [SM8850, QCS9075M]permissions:actions: read@@ -155,7 +155,7 @@ jobs:--pkg-dir pkg-snapdragon/llama.cpp \--model-url "https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF/resolve/main/Llama-3.2-1B-Instruct-Q4_0.gguf" \--device ${{ matrix.device }} \- ${{ startsWith(matrix.device, 'QCS') && '--retries 2 --retry-delay 300' || '' }}+ ${{ startsWith(matrix.device, 'QCS') && '--job-timeout 5400 --retries 2 --retry-delay 300' || '' }}env:QDC_API_KEY: ${{ secrets.QDC_API_KEY }}