[Core][Hybrid allocator + kv connector 1/n] Enable hybrid allocator + KV cache connector (#25712)

Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
Signed-off-by: Kuntai Du <kuntai@uchicago.edu>

tests/v1/kv_connector/unit/utils.py

@@ -91,6 +91,9 @@ def create_vllm_config(
         max_num_batched_tokens=max_num_batched_tokens,
         max_model_len=max_model_len,
         enable_chunked_prefill=enable_chunked_prefill,
+        # Disable hybrid KV cache manager for testing
+        # Should be removed after we support hybrid KV cache manager-based testing.
+        disable_hybrid_kv_cache_manager=True,
     )
     model_config = ModelConfig(
         model=model,