[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/v1/core/test_kv_cache_utils.py

@@ -695,11 +695,7 @@ def test_estimate_max_model_len(model_id, max_model_len,
     # Create a VllmConfig
     model_config = ModelConfig(
         model_id,
-        task="generate",
-        tokenizer=model_id,
-        tokenizer_mode="auto",
-        trust_remote_code=False,
-        seed=0,
+        runner="generate",
         dtype="float16",
         max_model_len=max_model_len,
     )
@@ -733,11 +729,7 @@ def test_get_max_concurrency_for_kv_cache_config():
     max_model_len = 16384
     model_config = ModelConfig(
         model_id,
-        task="generate",
-        tokenizer=model_id,
-        tokenizer_mode="auto",
-        trust_remote_code=False,
-        seed=0,
+        runner="generate",
         dtype="float16",
         max_model_len=max_model_len,
     )

tests/v1/core/test_scheduler.py

@@ -1248,9 +1248,6 @@ def create_scheduler_with_priority(
     )
     model_config = ModelConfig(
         model=model,
-        task="auto",
-        tokenizer=model,
-        tokenizer_mode="auto",
         trust_remote_code=True,
         dtype="float16",
         seed=42,

tests/v1/core/utils.py

@@ -59,9 +59,6 @@ def create_scheduler(
     )
     model_config = ModelConfig(
         model=model,
-        task="auto",
-        tokenizer=model,
-        tokenizer_mode="auto",
         trust_remote_code=True,
         dtype="float16",
         seed=42,