From 2cc5affc388d3d134bacc14f042405ead925531b Mon Sep 17 00:00:00 2001 From: Concurrensee Date: Thu, 11 Dec 2025 17:03:54 -0600 Subject: [PATCH] [ROCM][CI] Fix AMD Examples Test Group (#30276) Signed-off-by: Yida Wu Signed-off-by: Yida --- .buildkite/test-amd.yaml | 3 +-- examples/offline_inference/basic/embed.py | 8 ++++++++ examples/offline_inference/basic/score.py | 8 ++++++++ 3 files changed, 17 insertions(+), 2 deletions(-) diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml index 4038d32834e68..4e957634e7b47 100644 --- a/.buildkite/test-amd.yaml +++ b/.buildkite/test-amd.yaml @@ -435,7 +435,7 @@ steps: - label: Examples Test # 30min timeout_in_minutes: 45 - mirror_hardwares: [amdexperimental] + mirror_hardwares: [amdexperimental, amdproduction] agent_pool: mi325_1 # grade: Blocking working_dir: "/vllm-workspace/examples" @@ -455,7 +455,6 @@ steps: # for multi-modal models - python3 offline_inference/audio_language.py --seed 0 - python3 offline_inference/vision_language.py --seed 0 - - python3 offline_inference/vision_language_pooling.py --seed 0 - python3 offline_inference/vision_language_multi_image.py --seed 0 - python3 offline_inference/encoder_decoder_multimodal.py --model-type whisper --seed 0 # for pooling models diff --git a/examples/offline_inference/basic/embed.py b/examples/offline_inference/basic/embed.py index eeb7137ff7bae..17f727b33d321 100644 --- a/examples/offline_inference/basic/embed.py +++ b/examples/offline_inference/basic/embed.py @@ -4,6 +4,9 @@ from argparse import Namespace from vllm import LLM, EngineArgs +from vllm.attention.backends.registry import AttentionBackendEnum +from vllm.config import AttentionConfig +from vllm.platforms import current_platform from vllm.utils.argparse_utils import FlexibleArgumentParser @@ -20,6 +23,11 @@ def parse_args(): def main(args: Namespace): + if current_platform.is_rocm(): + args.attention_config = AttentionConfig( + backend=AttentionBackendEnum.FLEX_ATTENTION + ) + # Sample prompts. prompts = [ "Hello, my name is", diff --git a/examples/offline_inference/basic/score.py b/examples/offline_inference/basic/score.py index cbca50eb5efa8..b2dadffd249f5 100644 --- a/examples/offline_inference/basic/score.py +++ b/examples/offline_inference/basic/score.py @@ -4,6 +4,9 @@ from argparse import Namespace from vllm import LLM, EngineArgs +from vllm.attention.backends.registry import AttentionBackendEnum +from vllm.config import AttentionConfig +from vllm.platforms import current_platform from vllm.utils.argparse_utils import FlexibleArgumentParser @@ -20,6 +23,11 @@ def parse_args(): def main(args: Namespace): + if current_platform.is_rocm(): + args.attention_config = AttentionConfig( + backend=AttentionBackendEnum.FLEX_ATTENTION + ) + # Sample prompts. text_1 = "What is the capital of France?" texts_2 = [