Triton Inference Server

LiteLLM unterstützt Embedding-Modelle auf Triton Inference Servern

Eigenschaft	Details
Beschreibung	NVIDIA Triton Inference Server
Provider-Routing in LiteLLM	triton/
Unterstützte Operationen	/chat/completion, /completion, /embedding
Unterstützte Triton-Endpunkte	/infer, /generate, /embeddings
Link zur Anbieterdokumentation	Triton Inference Server ↗

Triton /generate - Chat Completion

SDK

Verwenden Sie das Präfix triton/, um an den Triton-Server weiterzuleiten

from litellm import completion
response = completion(
    model="triton/llama-3-8b-instruct",
    messages=[{"role": "user", "content": "who are u?"}],
    max_tokens=10,
    api_base="https://:8000/generate",
)

PROXY

1. Modelle zu Ihrer config.yaml hinzufügen

   model_list:
     - model_name: my-triton-model
       litellm_params:
         model: triton/<your-triton-model>"
         api_base: https://your-triton-api-base/triton/generate

2. Starten Sie den Proxy

   $ litellm --config /path/to/config.yaml --detailed_debug

3. Anfrage an LiteLLM Proxy Server senden

   OpenAI Python v1.0.0+

   import openai
   from openai import OpenAI
   
   # set base_url to your proxy server
   # set api_key to send to proxy server
   client = OpenAI(api_key="<proxy-api-key>", base_url="http://0.0.0.0:4000")
   
   response = client.chat.completions.create(
       model="my-triton-model",
       messages=[{"role": "user", "content": "who are u?"}],
       max_tokens=10,
   )
   
   print(response)
   

   curl

   --header ist optional, nur erforderlich, wenn Sie den litellm-Proxy mit virtuellen Schlüsseln verwenden

   curl --location 'http://0.0.0.0:4000/chat/completions' \
   --header 'Content-Type: application/json' \
   --header 'Authorization: Bearer sk-1234' \
   --data ' {
   "model": "my-triton-model",
   "messages": [{"role": "user", "content": "who are u?"}]
   }'
   

Triton /infer - Chat Completion

SDK

Verwenden Sie das Präfix triton/, um an den Triton-Server weiterzuleiten

from litellm import completion


response = completion(
    model="triton/llama-3-8b-instruct",
    messages=[{"role": "user", "content": "who are u?"}],
    max_tokens=10,
    api_base="https://:8000/infer",
)

PROXY

1. Modelle zu Ihrer config.yaml hinzufügen

   model_list:
     - model_name: my-triton-model
       litellm_params:
         model: triton/<your-triton-model>"
         api_base: https://your-triton-api-base/triton/infer

2. Starten Sie den Proxy

   $ litellm --config /path/to/config.yaml --detailed_debug

3. Anfrage an LiteLLM Proxy Server senden

   OpenAI Python v1.0.0+

   import openai
   from openai import OpenAI
   
   # set base_url to your proxy server
   # set api_key to send to proxy server
   client = OpenAI(api_key="<proxy-api-key>", base_url="http://0.0.0.0:4000")
   
   response = client.chat.completions.create(
       model="my-triton-model",
       messages=[{"role": "user", "content": "who are u?"}],
       max_tokens=10,
   )
   
   print(response)
   

   curl

   --header ist optional, nur erforderlich, wenn Sie den litellm-Proxy mit virtuellen Schlüsseln verwenden

   curl --location 'http://0.0.0.0:4000/chat/completions' \
   --header 'Content-Type: application/json' \
   --header 'Authorization: Bearer sk-1234' \
   --data ' {
   "model": "my-triton-model",
   "messages": [{"role": "user", "content": "who are u?"}]
   }'
   

Triton /embeddings - Embedding

SDK

Verwenden Sie das Präfix triton/, um an den Triton-Server weiterzuleiten

from litellm import embedding
import os

response = await litellm.aembedding(
    model="triton/<your-triton-model>",                                                       
    api_base="https://your-triton-api-base/triton/embeddings", # /embeddings endpoint you want litellm to call on your server
    input=["good morning from litellm"],
)

PROXY

1. Modelle zu Ihrer config.yaml hinzufügen

   model_list:
     - model_name: my-triton-model
       litellm_params:
         model: triton/<your-triton-model>"
         api_base: https://your-triton-api-base/triton/embeddings

2. Starten Sie den Proxy

   $ litellm --config /path/to/config.yaml --detailed_debug

3. Anfrage an LiteLLM Proxy Server senden

   OpenAI Python v1.0.0+

   import openai
   from openai import OpenAI
   
   # set base_url to your proxy server
   # set api_key to send to proxy server
   client = OpenAI(api_key="<proxy-api-key>", base_url="http://0.0.0.0:4000")
   
   response = client.embeddings.create(
       input=["hello from litellm"],
       model="my-triton-model"
   )
   
   print(response)
   

   curl

   --header ist optional, nur erforderlich, wenn Sie den litellm-Proxy mit virtuellen Schlüsseln verwenden

   curl --location 'http://0.0.0.0:4000/embeddings' \
   --header 'Content-Type: application/json' \
   --header 'Authorization: Bearer sk-1234' \
   --data ' {
   "model": "my-triton-model",
   "input": ["write a litellm poem"]
   }'