This commit is contained in:
Edward Ma 2025-01-27 13:21:43 -08:00
parent 1f0e399e32
commit 1d626bb212
4 changed files with 8 additions and 4 deletions

View file

@ -1 +1 @@
../../llama_stack/templates/sambanova/build.yaml
../../llama_stack/templates/sambanova/build.yaml

View file

@ -1 +1 @@
../../llama_stack/templates/sambanova/run.yaml
../../llama_stack/templates/sambanova/run.yaml

View file

@ -7,7 +7,12 @@
import json
from typing import AsyncGenerator
from llama_models.datatypes import CoreModelId, TopPSamplingStrategy, TopKSamplingStrategy, GreedySamplingStrategy
from llama_models.datatypes import (
CoreModelId,
GreedySamplingStrategy,
TopKSamplingStrategy,
TopPSamplingStrategy,
)
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.tokenizer import Tokenizer
from openai import OpenAI

View file

@ -30,4 +30,3 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda