From 3a6ae1d33c7a8ef28b6dfa978f53b4fdcdbaaca6 Mon Sep 17 00:00:00 2001 From: Simon Mo Date: Wed, 5 Jun 2024 17:49:27 -0500 Subject: [PATCH] [CI] Disable flash_attn backend for spec decode (#5286) --- .buildkite/test-pipeline.yaml | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml index 4edd1cad..02a4364d 100644 --- a/.buildkite/test-pipeline.yaml +++ b/.buildkite/test-pipeline.yaml @@ -45,7 +45,7 @@ steps: - TEST_DIST_MODEL=meta-llama/Llama-2-7b-hf DISTRIBUTED_EXECUTOR_BACKEND=mp pytest -v -s distributed/test_basic_distributed_correctness.py - TEST_DIST_MODEL=facebook/opt-125m DISTRIBUTED_EXECUTOR_BACKEND=mp pytest -v -s distributed/test_chunked_prefill_distributed.py - TEST_DIST_MODEL=meta-llama/Llama-2-7b-hf DISTRIBUTED_EXECUTOR_BACKEND=mp pytest -v -s distributed/test_chunked_prefill_distributed.py - - pytest -v -s spec_decode/e2e/test_integration_dist.py + - pytest -v -s spec_decode/e2e/test_integration_dist.py - label: Distributed Tests (Multiple Groups) #mirror_hardwares: [amd] @@ -124,7 +124,10 @@ steps: - label: Speculative decoding tests #mirror_hardwares: [amd] - command: pytest -v -s spec_decode + commands: + # See https://github.com/vllm-project/vllm/issues/5152 + - export VLLM_ATTENTION_BACKEND=XFORMERS + - pytest -v -s spec_decode - label: LoRA Test %N #mirror_hardwares: [amd]