DSPy: The framework for programming—not prompting—language models
Python
ci(llm): remove AMX backend variant to fix segfault on Sapphire Rapids runners (#10079)
Isaac Miller6f68dcdb3ef4
diff --git a/.github/workflows/run_tests.yml b/.github/workflows/run_tests.ymlindex 49396ffb2..9018e369e 100644--- a/.github/workflows/run_tests.yml+++ b/.github/workflows/run_tests.yml@@ -150,6 +150,12 @@ jobs:-p 11434:11434 \-v "$GITHUB_WORKSPACE/ollama-data:/root/.ollama" \ollama/ollama:0.31.2+ # Some GitHub runners are Sapphire-Rapids-class machines with AMX. llama.cpp's+ # AMX-repacked weight path segfaults there during model load (llama-server dies+ # with SIGSEGV in warm-up), while all non-AMX runners pass. Removing the AMX+ # backend variant makes ggml's autodetection fall back to the icelake kernels+ # that every other runner already uses.+ docker exec ollama rm /usr/lib/ollama/libggml-cpu-sapphirerapids.sotimeout 60 bash -c 'until curl -f http://localhost:11434/api/version; do sleep 2; done'- name: Pull LLMif: steps.cache-ollama.outputs.cache-hit != 'true'