scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-06 08:16:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

litellm_fix(hosted_vllm): use custom client when provided

Browse source 
When a custom OpenAI client is passed to hosted_vllm completion, use
openai_chat_completions.completion() to ensure the client is properly
used. This fixes test failures in test_openai_compatible_custom_api_base
and test_openai_compatible_custom_api_video for the hosted_vllm provider.

The base_llm_http_handler is still used when no custom client is passed,
preserving the ssl_verify functionality added in #19893.

Fixes: test_openai_compatible_custom_api_video[hosted_vllm]
Fixes: test_openai_compatible_custom_api_base[hosted_vllm]
This commit is contained in:
shin-bot-litellm 2026-01-31 17:59:14 +00:00
parent d5bc80bca9
commit d50b2eea75
1 changed files with 44 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

63
litellm/main.py
View file

@ -2385,25 +2385,50 @@ def completion( # type: ignore # noqa: PLR0915
api_base or litellm.api_base or get_secret_str("HOSTED_VLLM_API_BASE")
)
response = base_llm_http_handler.completion(
model=model,
messages=messages,
api_base=api_base,
custom_llm_provider=custom_llm_provider,
model_response=model_response,
encoding=_get_encoding(),
logging_obj=logging,
optional_params=optional_params,
timeout=timeout,
litellm_params=litellm_params,
shared_session=shared_session,
acompletion=acompletion,
stream=stream,
api_key=api_key,
headers=headers,
client=client,
provider_config=provider_config,
)
# If a custom OpenAI client is passed, use it via openai_chat_completions
# This ensures the client is properly used (e.g., for mocking in tests)
# Otherwise, use base_llm_http_handler for ssl_verify support
if client is not None:
response = openai_chat_completions.completion(
model=model,
messages=messages,
headers=headers,
model_response=model_response,
print_verbose=print_verbose,
api_key=api_key,
api_base=api_base,
acompletion=acompletion,
logging_obj=logging,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
timeout=timeout, # type: ignore
custom_prompt_dict=custom_prompt_dict,
client=client, # pass AsyncOpenAI, OpenAI client
organization=organization,
custom_llm_provider=custom_llm_provider,
shared_session=shared_session,
)
else:
response = base_llm_http_handler.completion(
model=model,
messages=messages,
api_base=api_base,
custom_llm_provider=custom_llm_provider,
model_response=model_response,
encoding=_get_encoding(),
logging_obj=logging,
optional_params=optional_params,
timeout=timeout,
litellm_params=litellm_params,
shared_session=shared_session,
acompletion=acompletion,
stream=stream,
api_key=api_key,
headers=headers,
client=client,
provider_config=provider_config,
)
logging.post_call(
input=messages, api_key=api_key, original_response=response
)