[CI][MiniCPM-o] Add MiniCPM-o 4.5 accuracy and performance coverage (#5524)

Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Signed-off-by: psv666 <2693925048@qq.com>
Co-authored-by: psv666 <2693925048@qq.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
This commit is contained in:
authored and GitHub committed 2026-08-11 14:53:49 +08:00
1 parent c4a14091c9
commit 322600bfb2
59 files changed
+1908 -155

No files matched your search

@@ -28,10 +28,13 @@ if _MODULE_NAME not in sys.modules:
_spec.loader.exec_module(_mod)
from vllm_omni.benchmarks.data_modules.seed_tts_dataset import ( # noqa: E402
SeedTTSDataset,
SeedTTSDesignDataset,
SeedTTSDesignSampleRequest,
SeedTTSSampleRequest,
SeedTTSTextDataset,
SeedTTSTextSampleRequest,
SeedTTSTurn,
)
# ---------------------------------------------------------------------------
@@ -70,6 +73,94 @@ def mock_tokenizer(mocker):
# ---------------------------------------------------------------------------
def test_seed_tts_dataset_groups_four_turns_with_one_reference(seed_tts_root, mock_tokenizer):
ds = SeedTTSDataset(
dataset_path=str(seed_tts_root),
random_seed=0,
locale="en",
disable_shuffle=True,
)
requests = ds.sample(
mock_tokenizer,
num_requests=1,
turns_per_session=4,
no_oversample=True,
)
assert len(requests) == 1
request = requests[0]
assert [turn.utterance_id for turn in request.seed_tts_turns] == [
"utt000",
"utt001",
"utt002",
"utt003",
]
assert [turn.target_text for turn in request.seed_tts_turns] == [
"target text 0",
"target text 1",
"target text 2",
"target text 3",
]
assert request.seed_tts_speech_extra["ref_text"] == "ref text 0"
assert request.seed_tts_ref_wav_path.endswith("utt000.wav")
def test_seed_tts_eval_expands_grouped_pcm_by_turn():
from vllm_omni.benchmarks.data_modules.seed_tts_eval import (
_expand_seed_tts_turn_outputs,
)
request = SeedTTSSampleRequest(
prompt="target 0",
prompt_len=4,
expected_output_len=100,
multi_modal_data=None,
request_id="session-0",
seed_tts_turns=tuple(
SeedTTSTurn(utterance_id=f"utt-{index}", target_text=f"target {index}") for index in range(4)
),
)
output = types.SimpleNamespace(
success=True,
tts_turn_pcm_bytes=[bytes([index]) for index in range(4)],
)
requests, outputs = _expand_seed_tts_turn_outputs([request], [output])
assert [item.prompt for item in requests] == [f"target {index}" for index in range(4)]
assert [item.seed_tts_utterance_id for item in requests] == [f"utt-{index}" for index in range(4)]
assert [item.tts_output_pcm_bytes for item in outputs] == [bytes([index]) for index in range(4)]
def test_seed_tts_eval_keeps_session_pcm_for_single_turn_chat():
"""Chat-omni Seed-TTS sets session PCM only; expand must not wipe it."""
from vllm_omni.benchmarks.data_modules.seed_tts_eval import (
_expand_seed_tts_turn_outputs,
)
request = SeedTTSSampleRequest(
prompt="target 0",
prompt_len=4,
expected_output_len=100,
multi_modal_data=None,
request_id="session-0",
seed_tts_turns=(SeedTTSTurn(utterance_id="utt-0", target_text="target 0"),),
)
pcm = b"\x01\x02\x03\x04"
output = types.SimpleNamespace(
success=True,
tts_output_pcm_bytes=pcm,
tts_turn_pcm_bytes=None,
)
requests, outputs = _expand_seed_tts_turn_outputs([request], [output])
assert len(requests) == 1
assert requests[0].prompt == "target 0"
assert outputs[0].tts_output_pcm_bytes == pcm
def test_seed_tts_text_dataset_omits_ref_audio(seed_tts_root, mock_tokenizer):
ds = SeedTTSTextDataset(
dataset_path=str(seed_tts_root),