diff --git a/.github/workflows/test_api_server.yml b/.github/workflows/test_api_server.yml index a3e04ea..8bfd67c 100644 --- a/.github/workflows/test_api_server.yml +++ b/.github/workflows/test_api_server.yml @@ -73,18 +73,20 @@ jobs: curl -LO https://huggingface.co/second-state/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct-Q3_K_M.gguf curl -LO https://huggingface.co/second-state/Nomic-embed-text-v1.5-Embedding-GGUF/resolve/main/nomic-embed-text-v1.5-f16.gguf - - name: Start rag-api-server for testing chat completions + - name: Start rag-api-server run: | nohup $HOME/.wasmedge/bin/wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2-1.5B-Instruct-Q3_K_M.gguf --nn-preload embedding:GGML:AUTO:nomic-embed-text-v1.5-f16.gguf rag-api-server.wasm --model-name Qwen2-1.5B-Instruct,nomic-embed-text-v1.5 --ctx-size 4096,512 --batch-size 16,512 --prompt-template chatml,embedding --socket-addr 0.0.0.0:8080 > ./start-llamaedge.log 2>&1 & - sleep 10 + sleep 5 cat start-llamaedge.log - name: Run test_chat.hurl run: | + sleep 5 hurl --test --jobs 1 ./tests/test_chat.hurl - name: Run test_embeddings.hurl run: | + sleep 5 hurl --test --jobs 1 ./tests/test_embeddings.hurl - name: Stop rag-api-server for testing chat completions