xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 13:44:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Add dummy maverick test to CI (#21324)

Browse Source 
Signed-off-by: Ming Yang <minos.future@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
Ming Yang 2025-07-23 20:22:42 -07:00 committed by GitHub
parent 63d92abb7c
commit 772ce5af97
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.buildkite/test-pipeline.yaml
View File

@ -718,6 +718,7 @@ steps:
- VLLM_USE_V1=0 CUDA_VISIBLE_DEVICES=0,1 pytest -v -s test_sharded_state_loader.py - VLLM_USE_V1=0 CUDA_VISIBLE_DEVICES=0,1 pytest -v -s test_sharded_state_loader.py
- VLLM_USE_V1=0 CUDA_VISIBLE_DEVICES=0,1 pytest -v -s kv_transfer/test_disagg.py - VLLM_USE_V1=0 CUDA_VISIBLE_DEVICES=0,1 pytest -v -s kv_transfer/test_disagg.py
- CUDA_VISIBLE_DEVICES=0,1 pytest -v -s v1/shutdown - CUDA_VISIBLE_DEVICES=0,1 pytest -v -s v1/shutdown
- pytest -v -s models/multimodal/generation/test_maverick.py
- label: Plugin Tests (2 GPUs) # 40min - label: Plugin Tests (2 GPUs) # 40min
mirror_hardwares: [amdexperimental] mirror_hardwares: [amdexperimental]

3
tests/models/multimodal/generation/test_maverick.py
View File

@ -23,6 +23,8 @@ from transformers import (AutoConfig, AutoProcessor, AutoTokenizer,
from vllm import LLM, SamplingParams from vllm import LLM, SamplingParams
from ....utils import multi_gpu_test
# Sample prompts for testing # Sample prompts for testing
PROMPTS: list[str] = [ PROMPTS: list[str] = [
"Hello, my name is", "Hello, my name is",
@ -541,6 +543,7 @@ def run_reduced_model(model_path: str,
print("-" * 40) print("-" * 40)
@multi_gpu_test(num_gpus=2)
@pytest.mark.parametrize( @pytest.mark.parametrize(
"original_model_name,text_layers,num_experts,vision_layers,", "original_model_name,text_layers,num_experts,vision_layers,",
[("meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", 4, 4, 2)]) [("meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", 4, 4, 2)])