phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

docs

Browse source
This commit is contained in:
ishaan-jaff 2023-09-08 14:10:05 -07:00
parent 632d928bfb
commit 99f08b45fc
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/my-website/docs/providers/vllm.md
View file

@ -12,7 +12,7 @@ pip install litellm vllm
import litellm import litellm
response = completion( response = completion(
model="vllm/facebook/opt-125m", model="vllm/facebook/opt-125m", # add a vllm prefix so litellm knows the custom_llm_provider==vllm
messages=messages, messages=messages,
temperature=0.2, temperature=0.2,
max_tokens=80) max_tokens=80)
@ -30,7 +30,7 @@ In order to use litellm to call a hosted vllm server add the following to your c
import litellm import litellm
response = completion( response = completion(
model="vllm/facebook/opt-125m", model="facebook/opt-125m", # pass the vllm model name
messages=messages, messages=messages,
api_base="https://hosted-vllm-api.co/v1", api_base="https://hosted-vllm-api.co/v1",
custom_llm_provider="openai", custom_llm_provider="openai",