Remove default values from InitVars so that they're not stored (#29859)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit 951445a52d)

tests/v1/core/test_kv_cache_utils.py

@@ -1128,7 +1128,11 @@ def test_estimate_max_model_len(model_id, max_model_len, want_estimated_max_len)
         dtype="float16",
         max_model_len=max_model_len,
     )
-    scheduler_config = SchedulerConfig(max_num_batched_tokens=32768)
+    scheduler_config = SchedulerConfig(
+        max_num_batched_tokens=32768,
+        max_model_len=model_config.max_model_len,
+        is_encoder_decoder=model_config.is_encoder_decoder,
+    )
 
     vllm_config = VllmConfig(
         model_config=model_config,
@@ -1163,7 +1167,10 @@ def test_get_max_concurrency_for_kv_cache_config():
         max_model_len=max_model_len,
     )
     scheduler_config = SchedulerConfig(
-        max_num_batched_tokens=1024, enable_chunked_prefill=True
+        max_num_batched_tokens=1024,
+        enable_chunked_prefill=True,
+        max_model_len=model_config.max_model_len,
+        is_encoder_decoder=model_config.is_encoder_decoder,
     )
 
     vllm_config = VllmConfig(

tests/v1/core/test_scheduler.py

@@ -1508,6 +1508,12 @@ def create_scheduler_with_priority(
     Returns:
       {class}`Scheduler` instance with priority scheduling
     """
+    model_config = ModelConfig(
+        model=model,
+        trust_remote_code=True,
+        dtype="float16",
+        seed=42,
+    )
     if max_model_len is None:
         max_model_len = max_num_batched_tokens
     scheduler_config = SchedulerConfig(
@@ -1517,14 +1523,9 @@ def create_scheduler_with_priority(
         long_prefill_token_threshold=long_prefill_token_threshold,
         disable_chunked_mm_input=disable_chunked_mm_input,
         enable_chunked_prefill=True,
+        is_encoder_decoder=model_config.is_encoder_decoder,
         policy="priority",  # Enable priority scheduling
     )
-    model_config = ModelConfig(
-        model=model,
-        trust_remote_code=True,
-        dtype="float16",
-        seed=42,
-    )
     # Cache config, optionally force APC
     cache_config = CacheConfig(
         block_size=block_size,

tests/v1/core/utils.py

@@ -69,6 +69,13 @@ def create_scheduler(
     Returns:
       {class}`Scheduler` instance
     """
+    model_config = ModelConfig(
+        model=model,
+        trust_remote_code=True,
+        dtype="float16",
+        seed=42,
+        skip_tokenizer_init=skip_tokenizer_init,
+    )
     if max_model_len is None:
         max_model_len = max_num_batched_tokens
     scheduler_config = SchedulerConfig(
@@ -79,13 +86,7 @@ def create_scheduler(
         disable_chunked_mm_input=disable_chunked_mm_input,
         enable_chunked_prefill=enable_chunked_prefill,
         async_scheduling=async_scheduling,
-    )
-    model_config = ModelConfig(
-        model=model,
-        trust_remote_code=True,
-        dtype="float16",
-        seed=42,
-        skip_tokenizer_init=skip_tokenizer_init,
+        is_encoder_decoder=model_config.is_encoder_decoder,
     )
     # Cache config, optionally force APC
     cache_config = CacheConfig(