phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-05 01:12:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix intergration tests

Browse source
This commit is contained in:
Honglin Cao 2025-03-11 11:18:50 -04:00
parent d1f67d90ca
commit a454b53bda
5 changed files with 9 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/remote/inference/centml/centml.py
View file

@ -8,7 +8,6 @@ from typing import AsyncGenerator, List, Optional, Union
from openai import OpenAI
from llama_stack import logcat
from llama_models.datatypes import CoreModelId
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.tokenizer import Tokenizer
@ -61,6 +60,10 @@ MODEL_ALIASES = [
"meta-llama/Llama-3.2-3B-Instruct",
CoreModelId.llama3_2_3b_instruct.value,
),
build_model_entry(
"meta-llama/Llama-3.3-70B-Instruct",
CoreModelId.llama3_3_70b_instruct.value,
),
]
@ -254,7 +257,6 @@ class CentMLInferenceAdapter(ModelRegistryHelper, Inference,
request.stream,
**self._build_options(request.sampling_params, request.logprobs, request.response_format),
}
logcat.debug("inference", f"params to centml: {params}")
return params
def _build_options(