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

[CI/Build] Fix VLM broadcast tests tensor_parallel_size passing (#10161)

Browse Source 
Signed-off-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Isotr0py 2024-11-09 12:02:59 +08:00 committed by GitHub
parent f83feccd7f
commit 47672f38b5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tests/models/decoder_only/vision_language/test_models.py
View File

@ -34,6 +34,7 @@ COMMON_BROADCAST_SETTINGS = {
"dtype": "half",
"max_tokens": 5,
"tensor_parallel_size": 2,
"model_kwargs": {"device_map": "auto"},
"image_size_factors": [(.25, 0.5, 1.0)],
"distributed_executor_backend": (
"ray",

1
tests/models/decoder_only/vision_language/vlm_utils/types.py
View File

@ -158,6 +158,7 @@ class VLMTestInfo(NamedTuple):
"max_model_len": self.max_model_len,
"max_num_seqs": self.max_num_seqs,
"task": self.task,
"tensor_parallel_size": self.tensor_parallel_size,
"hf_output_post_proc": self.hf_output_post_proc,
"vllm_output_post_proc": self.vllm_output_post_proc,
"auto_cls": self.auto_cls,