20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] Fix speculative decode seeded test (#6743)

Browse Source
This commit is contained in:
Nick Hill 2024-07-24 08:58:31 -07:00 committed by GitHub
parent 545146349c
commit 2cf0df3381
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 19 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tests/spec_decode/e2e/conftest.py
View File

@ -191,7 +191,8 @@ def create_llm_generator(baseline_or_test, request, common_llm_kwargs,
and llm.llm_engine.log_stats):
for sate_logger in llm.llm_engine.stat_loggers.values():
sate_logger.local_interval = 0
set_random_seed(seed)
if seed is not None:
set_random_seed(seed)
yield llm
del llm

22
tests/spec_decode/e2e/test_seed.py
View File

@ -21,7 +21,8 @@ from .conftest import run_equality_correctness_test
"num_speculative_tokens": 3,
}])
@pytest.mark.parametrize("per_test_common_llm_kwargs", [{}])
@pytest.mark.parametrize("baseline_llm_kwargs", [{}])
@pytest.mark.parametrize("baseline_llm_kwargs", [{"seed": 1}])
@pytest.mark.parametrize("test_llm_kwargs", [{"seed": 5}])
@pytest.mark.parametrize("batch_size", [1, 8, 32])
@pytest.mark.parametrize("temperature", [0.1, 1.0])
@pytest.mark.parametrize(
@ -30,15 +31,26 @@ from .conftest import run_equality_correctness_test
# Use smaller output len for fast test.
10,
])
@pytest.mark.parametrize("seed", [1])
def test_seeded_consistency(baseline_llm_generator, batch_size: int,
temperature: float, output_len: int):
@pytest.mark.parametrize("seed", [None])
def test_seeded_consistency(baseline_llm_generator, test_llm_generator,
batch_size: int, temperature: float,
output_len: int):
"""Verify outputs are consistent across multiple runs with same seed
"""
run_equality_correctness_test(baseline_llm_generator,
baseline_llm_generator,
test_llm_generator,
batch_size,
max_output_len=output_len,
temperature=temperature,
seeded=True,
force_output_len=True)
# Ensure this same test does fail if we _don't_ include per-request seeds
with pytest.raises(AssertionError):
run_equality_correctness_test(baseline_llm_generator,
test_llm_generator,
batch_size,
max_output_len=output_len,
temperature=temperature,
seeded=False,
force_output_len=True)