Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add tests for models #922

Merged
merged 13 commits into from
Sep 1, 2023
Merged

Add tests for models #922

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
10eddfd
Implement gelu_new
WoosukKwon Aug 22, 2023
aba9179
Add GeluNew
WoosukKwon Aug 22, 2023
ffd9506
Add gelu_fast
WoosukKwon Aug 22, 2023
4d8e275
Add test for model
WoosukKwon Aug 22, 2023
4aa8156
Merge branch 'main' into model-test
WoosukKwon Aug 30, 2023
8d20f5f
Fix model tests
WoosukKwon Aug 31, 2023
b4746e6
Add model test
WoosukKwon Aug 31, 2023
c179917
Minor
WoosukKwon Aug 31, 2023
22953fb
Minor
WoosukKwon Aug 31, 2023
55aca65
Increase max_tokens to 128
WoosukKwon Aug 31, 2023
8e43045
Use pytest.mark.parametrize
WoosukKwon Sep 1, 2023
f8a423c
Minor
WoosukKwon Sep 1, 2023
ac04105
Add dtype
WoosukKwon Sep 1, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Add dtype
  • Loading branch information
@WoosukKwon
WoosukKwon committed Sep 1, 2023
commit ac04105cdc88def7247cf81ec983f3449936ded5
2 changes: 1 addition & 1 deletion tests/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ def example_prompts() -> List[str]:
_STR_DTYPE_TO_TORCH_DTYPE = {
"half": torch.half,
"bfloat16": torch.bfloat16,
"float32": torch.float,
"float": torch.float,
}


Expand Down
6 changes: 4 additions & 2 deletions tests/models/test_models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,19 +18,21 @@


@pytest.mark.parametrize("model", MODELS)
@pytest.mark.parametrize("dtype", ["half"])
@pytest.mark.parametrize("max_tokens", [128])
def test_models(
hf_runner,
vllm_runner,
example_prompts,
model: str,
dtype: str,
max_tokens: int,
) -> None:
hf_model = hf_runner(model)
hf_model = hf_runner(model, dtype=dtype)
hf_outputs = hf_model.generate_greedy(example_prompts, max_tokens)
del hf_model

vllm_model = vllm_runner(model)
vllm_model = vllm_runner(model, dtype=dtype)
vllm_outputs = vllm_model.generate_greedy(example_prompts, max_tokens)
del vllm_model

Expand Down