biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Deprecation][2/N] Replace --task with --runner and --convert (#21470)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2025-07-28 10:42:40 +08:00
committed by GitHub
parent 8f605ee309
commit 86ae693f20
94 changed files with 1117 additions and 1083 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/entrypoints/openai/correctness/test_mteb_embed.py
View File

@@ -19,7 +19,8 @@ MAIN_SCORE = 0.7422994752439667
@pytest.fixture(scope="module")
def server():
args = [
"--task", "embed", "--enforce-eager", "--disable-uvicorn-access-log"
"--runner", "pooling", "--enforce-eager",
"--disable-uvicorn-access-log"
]
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:

3
tests/entrypoints/openai/correctness/test_mteb_score.py
View File

@@ -21,7 +21,8 @@ MODEL_NAME = "cross-encoder/ms-marco-MiniLM-L-6-v2"
@pytest.fixture(scope="module")
def server():
args = [
"--task", "score", "--enforce-eager", "--disable-uvicorn-access-log"
"--runner", "pooling", "--enforce-eager",
"--disable-uvicorn-access-log"
]
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:

4
tests/entrypoints/openai/test_chat_logit_bias_validation.py
View File

@@ -15,10 +15,6 @@ MODEL_NAME = "Qwen/Qwen2.5-1.5B-Instruct"
def get_vocab_size(model_name):
config = ModelConfig(
model=model_name,
task="auto",
tokenizer=model_name,
tokenizer_mode="auto",
trust_remote_code=False,
seed=0,
dtype="bfloat16",
)

1
tests/entrypoints/openai/test_chat_template.py
View File

@@ -102,6 +102,7 @@ def test_get_gen_prompt(model, template, add_generation_prompt,
tokenizer=model_info.tokenizer or model,
tokenizer_mode=model_info.tokenizer_mode,
trust_remote_code=model_info.trust_remote_code,
revision=model_info.revision,
hf_overrides=model_info.hf_overrides,
)

4
tests/entrypoints/openai/test_embedding.py
View File

@@ -33,8 +33,8 @@ def v1(run_with_both_engines):
@pytest.fixture(scope="module")
def server():
args = [
"--task",
"embed",
"--runner",
"pooling",
# use half precision for speed and memory savings in CI environment
"--dtype",
DTYPE,

4
tests/entrypoints/openai/test_embedding_dimensions.py
View File

@@ -42,8 +42,8 @@ def dtype(request):
@pytest.fixture(scope="module")
def server(model_info, dtype: str):
args = [
"--task",
"embed",
"--runner",
"pooling",
# use half precision for speed and memory savings in CI environment
"--dtype",
dtype,

2
tests/entrypoints/openai/test_openai_schema.py
View File

@@ -21,7 +21,7 @@ LONG_TIMEOUT_SECONDS: Final[int] = 60
@pytest.fixture(scope="module")
def server():
args = [
"--task",
"--runner",
"generate",
"--max-model-len",
"2048",

4
tests/entrypoints/openai/test_optional_middleware.py
View File

@@ -27,8 +27,8 @@ def server(request: pytest.FixtureRequest):
passed_params = [passed_params]
args = [
"--task",
"embed",
"--runner",
"pooling",
# use half precision for speed and memory savings in CI environment
"--dtype",
"float16",

4
tests/entrypoints/openai/test_pooling.py
View File

@@ -20,8 +20,8 @@ DUMMY_CHAT_TEMPLATE = """{% for message in messages %}{{message['role'] + ': ' +
@pytest.fixture(scope="module")
def server():
args = [
"--task",
"reward",
"--runner",
"pooling",
# use half precision for speed and memory savings in CI environment
"--dtype",
"bfloat16",

4
tests/entrypoints/openai/test_skip_tokenizer.py
View File

@@ -26,8 +26,8 @@ def v1(run_with_both_engines):
@pytest.fixture(scope="module")
def server():
args = [
"--task",
"embed",
"--runner",
"pooling",
# use half precision for speed and memory savings in CI environment
"--dtype",
DTYPE,

4
tests/entrypoints/openai/test_truncation.py
View File

@@ -29,8 +29,8 @@ input = """Immerse yourself in the enchanting chronicle of calculus, a
@pytest.fixture(scope="module")
def server():
args = [
"--task",
"embed",
"--runner",
"pooling",
"--dtype",
"bfloat16",
"--enforce-eager",

2
tests/entrypoints/openai/test_video.py
View File

@@ -25,7 +25,7 @@ TEST_VIDEO_URLS = [
@pytest.fixture(scope="module")
def server():
args = [
"--task",
"--runner",
"generate",
"--max-model-len",
"32768",

2
tests/entrypoints/openai/test_vision.py
View File

@@ -48,7 +48,7 @@ EXPECTED_MM_BEAM_SEARCH_RES = [
@pytest.fixture(scope="module")
def server():
args = [
"--task",
"--runner",
"generate",
"--max-model-len",
"2048",

4
tests/entrypoints/openai/test_vision_embedding.py
View File

@@ -31,8 +31,8 @@ TEST_IMAGE_URLS = [
@pytest.fixture(scope="module")
def server():
args = [
"--task",
"embed",
"--runner",
"pooling",
"--max-model-len",
"2048",
"--max-num-seqs",

42
tests/entrypoints/test_chat_utils.py
View File

@@ -47,12 +47,8 @@ MISTRAL_MODEL_ID = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
@pytest.fixture(scope="function")
def phi3v_model_config():
return ModelConfig(PHI3V_MODEL_ID,
task="generate",
tokenizer=PHI3V_MODEL_ID,
tokenizer_mode="auto",
runner="generate",
trust_remote_code=True,
dtype="auto",
seed=0,
limit_mm_per_prompt={
"image": 2,
})
@@ -61,12 +57,8 @@ def phi3v_model_config():
@pytest.fixture(scope="function")
def phi3v_model_config_mm_interleaved():
return ModelConfig(PHI3V_MODEL_ID,
task="generate",
tokenizer=PHI3V_MODEL_ID,
tokenizer_mode="auto",
runner="generate",
trust_remote_code=True,
dtype="auto",
seed=0,
interleave_mm_strings=True,
limit_mm_per_prompt={
"image": 2,
@@ -86,11 +78,7 @@ def phi3v_tokenizer():
@pytest.fixture(scope="function")
def qwen25omni_model_config_mm_interleaved():
return ModelConfig(QWEN25OMNI_MODEL_ID,
task="generate",
tokenizer=QWEN25OMNI_MODEL_ID,
tokenizer_mode="auto",
dtype="auto",
seed=0,
runner="generate",
interleave_mm_strings=True,
limit_mm_per_prompt={
"image": 2,
@@ -112,12 +100,7 @@ def qwen25omni_tokenizer():
@pytest.fixture(scope="module")
def mllama_model_config():
return ModelConfig(MLLAMA_MODEL_ID,
task="generate",
tokenizer=MLLAMA_MODEL_ID,
tokenizer_mode="auto",
trust_remote_code=True,
dtype="auto",
seed=0,
runner="generate",
limit_mm_per_prompt={
"image": 2,
})
@@ -136,12 +119,7 @@ def mllama_tokenizer():
@pytest.fixture(scope="function")
def mistral_model_config():
return ModelConfig(MISTRAL_MODEL_ID,
task="generate",
tokenizer=MISTRAL_MODEL_ID,
tokenizer_mode="auto",
trust_remote_code=True,
dtype="auto",
seed=0,
runner="generate",
limit_mm_per_prompt={
"image": 2,
})
@@ -1105,12 +1083,7 @@ def test_multimodal_image_parsing_matches_hf(model, image_url):
# Build a config for the model
model_config = ModelConfig(model,
task="generate",
tokenizer=model,
tokenizer_mode="auto",
trust_remote_code=True,
dtype="auto",
seed=0,
runner="generate",
limit_mm_per_prompt={
"image": 2,
})
@@ -1170,6 +1143,7 @@ def test_resolve_hf_chat_template(sample_json_schema, model, use_tools):
model,
tokenizer=model_info.tokenizer or model,
tokenizer_mode=model_info.tokenizer_mode,
revision=model_info.revision,
trust_remote_code=model_info.trust_remote_code,
hf_overrides=model_info.hf_overrides,
)
@@ -1225,6 +1199,7 @@ def test_resolve_content_format_hf_defined(model, expected_format):
model,
tokenizer=model_info.tokenizer or model,
tokenizer_mode=model_info.tokenizer_mode,
revision=model_info.revision,
trust_remote_code=model_info.trust_remote_code,
hf_overrides=model_info.hf_overrides,
)
@@ -1284,6 +1259,7 @@ def test_resolve_content_format_fallbacks(model, expected_format):
model,
tokenizer=model_info.tokenizer or model,
tokenizer_mode=model_info.tokenizer_mode,
revision=model_info.revision,
trust_remote_code=model_info.trust_remote_code,
hf_overrides=model_info.hf_overrides,
)