diff --git a/tests/e2e/vLLM/configs/fp8_block.yaml b/tests/e2e/vLLM/configs/fp8_block.yaml new file mode 100644 index 000000000..3d0c0512e --- /dev/null +++ b/tests/e2e/vLLM/configs/fp8_block.yaml @@ -0,0 +1,4 @@ +cadence: "nightly" +test_type: "regression" +model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 +scheme: FP8_BLOCK