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

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>

tests/entrypoints/openai/correctness/test_mteb_embed.py

@@ -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:

tests/entrypoints/openai/correctness/test_mteb_score.py

@@ -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:

tests/entrypoints/openai/test_chat_logit_bias_validation.py

@@ -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",
     )

tests/entrypoints/openai/test_chat_template.py

@@ -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,
     )
 

tests/entrypoints/openai/test_embedding.py

@@ -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,

tests/entrypoints/openai/test_embedding_dimensions.py

@@ -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,

tests/entrypoints/openai/test_openai_schema.py

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

tests/entrypoints/openai/test_optional_middleware.py

@@ -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",

tests/entrypoints/openai/test_pooling.py

@@ -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",

tests/entrypoints/openai/test_skip_tokenizer.py

@@ -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,

tests/entrypoints/openai/test_truncation.py

@@ -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",

tests/entrypoints/openai/test_video.py

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

tests/entrypoints/openai/test_vision.py

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

tests/entrypoints/openai/test_vision_embedding.py

@@ -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",