scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-20 00:11:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 134

Merge pull request #41640 from BerriAI/litellm_remove_dead_provider_config_test_blocks

Browse source 
chore(tests): remove commented-out hf, petals and vertex ai completion blocks
This commit is contained in:
Mateo Wang 2026-09-17 17:55:12 -07:00 • committed by GitHub
commit a7dc6551c0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 0 additions and 89 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

89
tests/local_testing/test_provider_specific_config.py
View file

@ -12,36 +12,6 @@ from unittest.mock import AsyncMock, MagicMock, patch
import litellm
from litellm import RateLimitError, completion
# Huggingface - Expensive to deploy models and keep them running. Maybe we can try doing this via baseten??
# def hf_test_completion_tgi():
# litellm.HuggingfaceConfig(max_new_tokens=200)
# litellm.set_verbose=True
# try:
# # OVERRIDE WITH DYNAMIC MAX TOKENS
# response_1 = litellm.completion(
# model="huggingface/mistralai/Mistral-7B-Instruct-v0.1",
# messages=[{ "content": "Hello, how are you?","role": "user"}],
# api_base="https://n9ox93a8sv5ihsow.us-east-1.aws.endpoints.huggingface.cloud",
# max_tokens=10
# )
# # Add any assertions here to check the response
# print(response_1)
# response_1_text = response_1.choices[0].message.content
# # USE CONFIG TOKENS
# response_2 = litellm.completion(
# model="huggingface/mistralai/Mistral-7B-Instruct-v0.1",
# messages=[{ "content": "Hello, how are you?","role": "user"}],
# api_base="https://n9ox93a8sv5ihsow.us-east-1.aws.endpoints.huggingface.cloud",
# )
# # Add any assertions here to check the response
# print(response_2)
# response_2_text = response_2.choices[0].message.content
# assert len(response_2_text) > len(response_1_text)
# except Exception as e:
# pytest.fail(f"Error occurred: {e}")
# hf_test_completion_tgi()
# Anthropic
@ -322,65 +292,6 @@ def aleph_alpha_test_completion():
# aleph_alpha_test_completion()
# Petals - calls are too slow, will cause circle ci to fail due to delay. Test locally.
# def petals_completion():
# litellm.PetalsConfig(max_new_tokens=10)
# # litellm.set_verbose=True
# try:
# # OVERRIDE WITH DYNAMIC MAX TOKENS
# response_1 = litellm.completion(
# model="petals/petals-team/StableBeluga2",
# messages=[{ "content": "Hello, how are you? Be as verbose as possible","role": "user"}],
# api_base="https://chat.petals.dev/api/v1/generate",
# max_tokens=100
# )
# response_1_text = response_1.choices[0].message.content
# print(f"response_1_text: {response_1_text}")
# # USE CONFIG TOKENS
# response_2 = litellm.completion(
# model="petals/petals-team/StableBeluga2",
# api_base="https://chat.petals.dev/api/v1/generate",
# messages=[{ "content": "Hello, how are you? Be as verbose as possible","role": "user"}],
# )
# response_2_text = response_2.choices[0].message.content
# print(f"response_2_text: {response_2_text}")
# assert len(response_2_text) < len(response_1_text)
# except Exception as e:
# pytest.fail(f"Error occurred: {e}")
# petals_completion()
# VertexAI
# We don't have vertex ai configured for circle ci yet -- need to figure this out.
# def vertex_ai_test_completion():
# litellm.VertexAIConfig(max_output_tokens=10)
# # litellm.set_verbose=True
# try:
# # OVERRIDE WITH DYNAMIC MAX TOKENS
# response_1 = litellm.completion(
# model="chat-bison",
# messages=[{ "content": "Hello, how are you? Be as verbose as possible","role": "user"}],
# max_tokens=100
# )
# response_1_text = response_1.choices[0].message.content
# print(f"response_1_text: {response_1_text}")
# # USE CONFIG TOKENS
# response_2 = litellm.completion(
# model="chat-bison",
# messages=[{ "content": "Hello, how are you? Be as verbose as possible","role": "user"}],
# )
# response_2_text = response_2.choices[0].message.content
# print(f"response_2_text: {response_2_text}")
# assert len(response_2_text) < len(response_1_text)
# except Exception as e:
# pytest.fail(f"Error occurred: {e}")
# vertex_ai_test_completion()
# Sagemaker