phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

chore: remove dependency on llama_models completely (#1344)

Browse source
This commit is contained in:
Ashwin Bharambe 2025-03-01 12:48:08 -08:00 • committed by GitHub
parent 7131d5ddeb
commit 8bbd52bb9f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
43 changed files with 131358 additions and 202 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -9,7 +9,6 @@ import os
import uuid
from typing import AsyncGenerator, List, Optional
from llama_models.llama3.api.tokenizer import Tokenizer
from vllm.engine.arg_utils import AsyncEngineArgs
from vllm.engine.async_llm_engine import AsyncLLMEngine
from vllm.sampling_params import SamplingParams as VLLMSamplingParams
@ -36,6 +35,7 @@ from llama_stack.apis.inference import (
ToolPromptFormat,
)
from llama_stack.apis.models import Model
from llama_stack.models.llama.llama3.tokenizer import Tokenizer
from llama_stack.models.llama.sku_list import resolve_model
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.openai_compat import (