phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Litellm vllm refactor (#7158)

Browse source 
* refactor(vllm/): move vllm to use base llm config

* test: mark flaky test
This commit is contained in:
Krish Dholakia 2024-12-10 21:48:35 -08:00 • committed by GitHub
parent e9fbefca5d
commit cd9b92b402
9 changed files with 48 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/main.py
View file

@ -94,7 +94,6 @@ from .llms import (
palm,
petals,
replicate,
vllm,
)
from .llms.ai21 import completion as ai21
from .llms.anthropic.chat import AnthropicChatCompletion
@ -160,6 +159,7 @@ from .llms.vertex_ai_and_google_ai_studio.vertex_embeddings.embedding_handler im
from .llms.vertex_ai_and_google_ai_studio.vertex_model_garden.main import (
VertexAIModelGardenModels,
)
from .llms.vllm.completion import handler
from .llms.watsonx.chat.handler import WatsonXChatHandler
from .llms.watsonx.completion.handler import IBMWatsonXAI
from .types.llms.openai import (
@ -2691,7 +2691,7 @@ def completion( # type: ignore # noqa: PLR0915
response = response
elif custom_llm_provider == "vllm":
custom_prompt_dict = custom_prompt_dict or litellm.custom_prompt_dict
model_response = vllm.completion(
model_response = handler.completion(
model=model,
messages=messages,
custom_prompt_dict=custom_prompt_dict,