Skip to content

[tests] add cb parameterization #289

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

Merged
merged 7 commits into from
Jul 8, 2025
Merged

[tests] add cb parameterization #289

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
786a778
🎨 add cb parameterization
prashantgupta24 Jul 8, 2025
e85cf2c
🎨 set max_model_len to 128 for cb
prashantgupta24 Jul 8, 2025
0b6581e
🎨 fmt
prashantgupta24 Jul 8, 2025
ad9002c
🎨 fmt
prashantgupta24 Jul 8, 2025
bc39adb
🎨 set to 256 for consistency
prashantgupta24 Jul 8, 2025
a501cf6
🎨 fix indentation
prashantgupta24 Jul 8, 2025
000ed74
🎨 fix indentation
prashantgupta24 Jul 8, 2025
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
17 changes: 14 additions & 3 deletions tests/e2e/test_spyre_max_new_tokens.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,8 @@
from vllm import SamplingParams


@pytest.mark.parametrize("cb",
[pytest.param(1, marks=pytest.mark.cb, id="cb"), 0])
@pytest.mark.parametrize("model", get_spyre_model_list())
@pytest.mark.parametrize("stop_last", [True, False])
@pytest.mark.parametrize(
Expand All @@ -20,6 +22,7 @@ def test_output(
stop_last: bool,
warmup_shape: tuple[int, int, int],
backend: str,
cb: int,
monkeypatch: pytest.MonkeyPatch,
) -> None:
'''
Expand Down Expand Up @@ -66,16 +69,24 @@ def test_output(
] + vllm_sampling_params
hf_max_new_tokens = [max_new_tokens_early_stop] + hf_max_new_tokens

kwargs = ({
"max_num_seqs": 2,
"use_cb": True,
"max_model_len": 256
} if cb == 1 else {
"warmup_shapes": (warmup_shape, ),
"max_model_len": 2048
})

vllm_results = generate_spyre_vllm_output(
model=model,
prompts=prompts,
warmup_shapes=[warmup_shape],
max_model_len=2048,
block_size=2048,
sampling_params=vllm_sampling_params,
tensor_parallel_size=1,
backend=backend,
monkeypatch=monkeypatch)
monkeypatch=monkeypatch,
**kwargs)

hf_results = generate_hf_output(model=model,
prompts=prompts,
Expand Down