diff --git a/vllm/v1/engine/async_llm.py b/vllm/v1/engine/async_llm.py
index 0d646d8dd575..74c2251c7521 100644
--- a/vllm/v1/engine/async_llm.py
+++ b/vllm/v1/engine/async_llm.py
@@ -20,6 +20,8 @@
 from vllm.pooling_params import PoolingParams
 from vllm.prompt_adapter.request import PromptAdapterRequest
 from vllm.sampling_params import SamplingParams
+from vllm.transformers_utils.config import (
+    maybe_register_config_serialize_by_value)
 from vllm.transformers_utils.tokenizer import AnyTokenizer
 from vllm.transformers_utils.tokenizer_group import init_tokenizer_from_configs
 from vllm.usage.usage_lib import UsageContext
@@ -80,6 +82,9 @@ def __init__(
                 "AsyncLLMEngine.from_vllm_config(...) or explicitly set "
                 "VLLM_USE_V1=0 or 1 and report this issue on Github.")
 
+        # Ensure we can serialize custom transformer configs
+        maybe_register_config_serialize_by_value()
+
         self.model_config = vllm_config.model_config
         self.vllm_config = vllm_config
         self.log_requests = log_requests