phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[Feat] Add max_completion_tokens param (#5691)

Browse source 
* add max_completion_tokens

* add max_completion_tokens

* add max_completion_tokens support for OpenAI models

* add max_completion_tokens param

* add max_completion_tokens for bedrock converse models

* add test for converse maxTokens

* fix openai o1 param mapping test

* move test optional params

* add max_completion_tokens for anthropic api

* fix conftest

* add max_completion tokens for vertex ai partner models

* add max_completion_tokens for fireworks ai

* add max_completion_tokens for hf rest api

* add test for param mapping

* add param mapping for vertex, gemini + testing

* predibase is the most unstable and unusable llm api in prod, can't handle our ci/cd

* add max_completion_tokens to openai supported params

* fix fireworks ai param mapping
This commit is contained in:
Ishaan Jaff 2024-09-14 14:57:01 -07:00 • committed by GitHub
parent 415a3ede9e
commit 85acdb9193
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
31 changed files with 591 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

7
litellm/llms/nvidia_nim.py
View file

@ -78,6 +78,7 @@ class NvidiaNimConfig:
"temperature",
"top_p",
"max_tokens",
"max_completion_tokens",
]
elif model == "nvidia/nemotron-4-340b-reward":
return [
@ -92,6 +93,7 @@ class NvidiaNimConfig:
"frequency_penalty",
"presence_penalty",
"max_tokens",
"max_completion_tokens",
"stop",
]
else:
@ -124,6 +126,7 @@ class NvidiaNimConfig:
"frequency_penalty",
"presence_penalty",
"max_tokens",
"max_completion_tokens",
"stop",
"seed",
]
@ -133,6 +136,8 @@ class NvidiaNimConfig:
) -> dict:
supported_openai_params = self.get_supported_openai_params(model=model)
for param, value in non_default_params.items():
if param in supported_openai_params:
if param == "max_completion_tokens":
optional_params["max_tokens"] = value
elif param in supported_openai_params:
optional_params[param] = value
return optional_params