owen/worker-vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix: openai tool calling

Browse Source
This commit is contained in:
kldzj
2024-12-06 13:08:48 +01:00
parent d9f54ce76a
commit 3e86d16892
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/engine.py
+3 -1
View File
@@ -17,7 +17,7 @@ from vllm.entrypoints.openai.serving_engine import BaseModelPath, LoRAModulePath
from utils import DummyRequest, JobInput, BatchSize, create_error_response from utils import DummyRequest, JobInput, BatchSize, create_error_response
from constants import DEFAULT_MAX_CONCURRENCY, DEFAULT_BATCH_SIZE, DEFAULT_BATCH_SIZE_GROWTH_FACTOR, DEFAULT_MIN_BATCH_SIZE from constants import DEFAULT_MAX_CONCURRENCY, DEFAULT_BATCH_SIZE, DEFAULT_BATCH_SIZE_GROWTH_FACTOR, DEFAULT_MIN_BATCH_SIZE
from tokenizer import TokenizerWrapper from tokenizer import TokenizerWrapper
from engine_args import get_engine_args from engine_args import get_engine_args, DEFAULT_ARGS
class vLLMEngine: class vLLMEngine:
def __init__(self, engine = None): def __init__(self, engine = None):
@@ -146,6 +146,8 @@ class OpenAIvLLMEngine(vLLMEngine):
base_model_paths=self.base_model_paths, base_model_paths=self.base_model_paths,
response_role=self.response_role, response_role=self.response_role,
chat_template=self.tokenizer.tokenizer.chat_template, chat_template=self.tokenizer.tokenizer.chat_template,
enable_auto_tools=DEFAULT_ARGS.enable_auto_tool_choice,
tool_parser=DEFAULT_ARGS.tool_call_parser,
lora_modules=lora_modules, lora_modules=lora_modules,
prompt_adapters=None, prompt_adapters=None,
request_logger=None request_logger=None