biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc][LoRA] Ensure Lora Adapter requests return adapter name (#11094)

Browse Source 
Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jiaxin Shan
2024-12-12 01:25:16 -08:00
committed by GitHub
parent 62de37a38e
commit 85362f028c
4 changed files with 33 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
tests/entrypoints/openai/test_serving_engine.py
View File

@@ -9,6 +9,7 @@ from vllm.entrypoints.openai.protocol import (ErrorResponse,
LoadLoraAdapterRequest,
UnloadLoraAdapterRequest)
from vllm.entrypoints.openai.serving_engine import BaseModelPath, OpenAIServing
from vllm.lora.request import LoRARequest
MODEL_NAME = "meta-llama/Llama-2-7b"
BASE_MODEL_PATHS = [BaseModelPath(name=MODEL_NAME, model_path=MODEL_NAME)]
@@ -33,6 +34,16 @@ async def _async_serving_engine_init():
return serving_engine
@pytest.mark.asyncio
async def test_serving_model_name():
serving_engine = await _async_serving_engine_init()
assert serving_engine._get_model_name(None) == MODEL_NAME
request = LoRARequest(lora_name="adapter",
lora_path="/path/to/adapter2",
lora_int_id=1)
assert serving_engine._get_model_name(request) == request.lora_name
@pytest.mark.asyncio
async def test_load_lora_adapter_success():
serving_engine = await _async_serving_engine_init()