mirror of
https://github.com/bentoml/OpenLLM.git
synced 2026-03-09 02:32:51 -04:00
revert: configuration not to dump flatten (#597)
Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
@@ -56,7 +56,7 @@ _Metadata = openllm.MetadataOutput(
|
||||
model_name=llm_config['model_name'],
|
||||
backend=llm.__llm_backend__,
|
||||
model_id=llm.model_id,
|
||||
configuration=llm_config.model_dump_json(flatten=True).decode(),
|
||||
configuration=llm_config.model_dump_json().decode(),
|
||||
prompt_template=llm.runner.prompt_template,
|
||||
system_message=llm.runner.system_message,
|
||||
)
|
||||
@@ -67,6 +67,5 @@ def metadata_v1(_: str) -> openllm.MetadataOutput:
|
||||
return _Metadata
|
||||
|
||||
|
||||
openllm.mount_entrypoints(
|
||||
svc, llm
|
||||
) # HACK: This must always be the last line in this file, as we will do some MK for OpenAPI schema.
|
||||
# HACK: This must always be the last line in this file, as we will do some MK for OpenAPI schema.
|
||||
openllm.mount_entrypoints(svc, llm)
|
||||
|
||||
Reference in New Issue
Block a user