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

[Refactor] [7/N] to simplify the vLLM lora serving architecture (#32251)

Browse Source 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-13 23:37:34 +08:00
committed by GitHub
parent 252c011012
commit 4f02cb2eac
5 changed files with 23 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/entrypoints/openai/test_serving_models.py
View File

@@ -10,10 +10,12 @@ from vllm.config import ModelConfig
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
)
from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
from vllm.entrypoints.serve.lora.protocol import (
LoadLoRAAdapterRequest,
UnloadLoRAAdapterRequest,
)
from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
from vllm.lora.request import LoRARequest
MODEL_NAME = "hmellor/tiny-random-LlamaForCausalLM"