biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Core] Dynamic image size support for VLMs (#5276)

Browse Source 
Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: ywang96 <ywang@roblox.com>
Co-authored-by: xwjiang2010 <87673679+xwjiang2010@users.noreply.github.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2024-07-03 11:34:00 +08:00
committed by GitHub
parent 482045ee77
commit 9831aec49f
38 changed files with 1453 additions and 664 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
tests/distributed/test_multimodal_broadcast.py
View File

@@ -30,9 +30,10 @@ else:
@pytest.mark.parametrize("tensor_parallel_size", [2])
@pytest.mark.parametrize("dtype", ["half"])
@pytest.mark.parametrize("max_tokens", [128])
@pytest.mark.parametrize("num_logprobs", [5])
def test_models(hf_runner, vllm_runner, image_assets,
tensor_parallel_size: int, dtype: str,
max_tokens: int) -> None:
tensor_parallel_size: int, dtype: str, max_tokens: int,
num_logprobs: int) -> None:
if cuda_device_count_stateless() < tensor_parallel_size:
pytest.skip(
f"Need at least {tensor_parallel_size} GPUs to run the test.")
@@ -44,8 +45,10 @@ def test_models(hf_runner, vllm_runner, image_assets,
vllm_runner,
image_assets,
model_and_config=model_and_vl_config[0],
size_factors=[1.0],
dtype=dtype,
max_tokens=max_tokens,
num_logprobs=num_logprobs,
tensor_parallel_size=tensor_parallel_size,
distributed_executor_backend=distributed_executor_backend,
)