xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-31 05:07:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

[ROCM][CI] Fix AMD Examples Test Group (#30276)

Browse Source 
Signed-off-by: Yida Wu <yida.wu@amd.com>
Signed-off-by: Yida <yida.wu@amd.com>
This commit is contained in:
Concurrensee 2025-12-11 17:03:54 -06:00 committed by GitHub
parent a00d88973d
commit 2cc5affc38
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 17 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.buildkite/test-amd.yaml
View File

@ -435,7 +435,7 @@ steps:
- label: Examples Test # 30min - label: Examples Test # 30min
timeout_in_minutes: 45 timeout_in_minutes: 45
mirror_hardwares: [amdexperimental] mirror_hardwares: [amdexperimental, amdproduction]
agent_pool: mi325_1 agent_pool: mi325_1
# grade: Blocking # grade: Blocking
working_dir: "/vllm-workspace/examples" working_dir: "/vllm-workspace/examples"
@ -455,7 +455,6 @@ steps:
# for multi-modal models # for multi-modal models
- python3 offline_inference/audio_language.py --seed 0 - python3 offline_inference/audio_language.py --seed 0
- python3 offline_inference/vision_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/vision_language_multi_image.py --seed 0
- python3 offline_inference/encoder_decoder_multimodal.py --model-type whisper --seed 0 - python3 offline_inference/encoder_decoder_multimodal.py --model-type whisper --seed 0
# for pooling models # for pooling models

8
examples/offline_inference/basic/embed.py
View File

@ -4,6 +4,9 @@
from argparse import Namespace from argparse import Namespace
from vllm import LLM, EngineArgs 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 from vllm.utils.argparse_utils import FlexibleArgumentParser
@ -20,6 +23,11 @@ def parse_args():
def main(args: Namespace): def main(args: Namespace):
if current_platform.is_rocm():
args.attention_config = AttentionConfig(
backend=AttentionBackendEnum.FLEX_ATTENTION
)
# Sample prompts. # Sample prompts.
prompts = [ prompts = [
"Hello, my name is", "Hello, my name is",

8
examples/offline_inference/basic/score.py
View File

@ -4,6 +4,9 @@
from argparse import Namespace from argparse import Namespace
from vllm import LLM, EngineArgs 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 from vllm.utils.argparse_utils import FlexibleArgumentParser
@ -20,6 +23,11 @@ def parse_args():
def main(args: Namespace): def main(args: Namespace):
if current_platform.is_rocm():
args.attention_config = AttentionConfig(
backend=AttentionBackendEnum.FLEX_ATTENTION
)
# Sample prompts. # Sample prompts.
text_1 = "What is the capital of France?" text_1 = "What is the capital of France?"
texts_2 = [ texts_2 = [