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

remove conflicting default for tool prompt format in chat completion (#742)

Browse source 
# What does this PR do?
We are setting a default value of json for tool prompt format, which
conflicts with llama 3.2/3.3 models since they use python list. This PR
changes the defaults to None and in the code, we infer default based on
the model.

Addresses: #695 

Tests:
❯ LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v
tests/client-sdk/inference/test_inference.py -k
"test_text_chat_completion"

 pytest llama_stack/providers/tests/inference/test_prompt_adapter.py
This commit is contained in:
Dinesh Yeduguru 2025-01-10 10:41:53 -08:00 • committed by GitHub
parent 24fa1adc2f
commit 8af6951106
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 27 additions and 91 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -10,10 +10,8 @@ import uuid
from typing import AsyncGenerator, List, Optional
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_models.sku_list import resolve_model
from vllm.engine.arg_utils import AsyncEngineArgs
from vllm.engine.async_llm_engine import AsyncLLMEngine
from vllm.sampling_params import SamplingParams as VLLMSamplingParams
@ -36,7 +34,6 @@ from llama_stack.apis.inference import (
ToolPromptFormat,
)
from llama_stack.apis.models import Model
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.openai_compat import (
OpenAICompatCompletionChoice,
@ -50,7 +47,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
from .config import VLLMConfig
log = logging.getLogger(__name__)
@ -146,7 +142,7 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
sampling_params: Optional[SamplingParams] = SamplingParams(),
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
tool_prompt_format: Optional[ToolPromptFormat] = None,
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,