Skip to content

add changes for lora adapter support and /v1/models endpoint #121

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 31, 2024
+15 −6
Merged

add changes for lora adapter support and /v1/models endpoint #121

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5cd12ba
add changes for lora adapter support and /v1/models endpoint
sven-knoblauch Oct 9, 2024
677a01e
update code for case of no lora adapter
sven-knoblauch Oct 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 15 additions & 6 deletions src/engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,8 @@
from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
from vllm.entrypoints.openai.serving_completion import OpenAIServingCompletion
from vllm.entrypoints.openai.protocol import ChatCompletionRequest, CompletionRequest, ErrorResponse
from vllm.entrypoints.openai.serving_engine import BaseModelPath
from vllm.entrypoints.openai.serving_engine import BaseModelPath, LoRAModulePath


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
Expand Down Expand Up @@ -128,21 +129,32 @@ async def _initialize_engines(self):
self.base_model_paths = [
BaseModelPath(name=self.engine_args.model, model_path=self.engine_args.model)
]

lora_modules = os.getenv('LORA_MODULES', None)
if lora_modules is not None:
try:
lora_modules = json.loads(lora_modules)
lora_modules = [LoRAModulePath(**lora_modules)]
except:
lora_modules = None



self.chat_engine = OpenAIServingChat(
engine_client=self.llm,
model_config=self.model_config,
base_model_paths=self.base_model_paths,
response_role=self.response_role,
chat_template=self.tokenizer.tokenizer.chat_template,
lora_modules=None,
lora_modules=lora_modules,
prompt_adapters=None,
request_logger=None
)
self.completion_engine = OpenAIServingCompletion(
engine_client=self.llm,
model_config=self.model_config,
base_model_paths=self.base_model_paths,
lora_modules=[],
lora_modules=lora_modules,
prompt_adapters=None,
request_logger=None
)
Expand All @@ -158,9 +170,6 @@ async def generate(self, openai_request: JobInput):

async def _handle_model_request(self):
models = await self.chat_engine.show_available_models()
fixed_model = models.data[0]
fixed_model.id = self.served_model_name
models.data = [fixed_model]
return models.model_dump()

async def _handle_chat_or_completion_request(self, openai_request: JobInput):
Expand Down