phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 17:29:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

vllm

Browse source
This commit is contained in:
Xi Yan 2024-12-26 18:25:28 -08:00
parent 206554e853
commit 6596caed55
1 changed files with 21 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

25
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -7,10 +7,10 @@
import logging import logging
import os import os
import uuid import uuid
from typing import AsyncGenerator, Optional from typing import AsyncGenerator, List, Optional
from llama_models.llama3.api.chat_format import ChatFormat from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.datatypes import * # noqa: F403
from llama_models.llama3.api.tokenizer import Tokenizer from llama_models.llama3.api.tokenizer import Tokenizer
from llama_models.sku_list import resolve_model from llama_models.sku_list import resolve_model
@ -18,9 +18,26 @@ from vllm.engine.arg_utils import AsyncEngineArgs
from vllm.engine.async_llm_engine import AsyncLLMEngine from vllm.engine.async_llm_engine import AsyncLLMEngine
from vllm.sampling_params import SamplingParams as VLLMSamplingParams from vllm.sampling_params import SamplingParams as VLLMSamplingParams
from llama_stack.apis.inference import * # noqa: F403 from llama_stack.apis.common.content_types import InterleavedContent
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
ChatCompletionResponseStreamChunk,
CompletionResponse,
CompletionResponseStreamChunk,
EmbeddingsResponse,
Inference,
LogProbConfig,
Message,
ResponseFormat,
SamplingParams,
ToolChoice,
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.models import Model
from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.openai_compat import ( from llama_stack.providers.utils.inference.openai_compat import (
OpenAICompatCompletionChoice, OpenAICompatCompletionChoice,
OpenAICompatCompletionResponse, OpenAICompatCompletionResponse,