[LoRA] Cleanup LoRA unused code (#29611)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

tests/entrypoints/openai/test_models.py

@@ -8,13 +8,13 @@ import pytest_asyncio
 from ...utils import RemoteOpenAIServer
 
 # any model with a chat template should work here
-MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
+MODEL_NAME = "Qwen/Qwen3-0.6B"
 # technically this needs Mistral-7B-v0.1 as base, but we're not testing
 # generation quality here
 
 
 @pytest.fixture(scope="module")
-def server(zephyr_lora_files):
+def server(qwen3_lora_files):
     args = [
         # use half precision for speed and memory savings in CI environment
         "--dtype",
@@ -25,7 +25,7 @@ def server(zephyr_lora_files):
         # lora config below
         "--enable-lora",
         "--lora-modules",
-        f"zephyr-lora={zephyr_lora_files}",
+        f"qwen3-lora={qwen3_lora_files}",
         "--max-lora-rank",
         "64",
         "--max-cpu-loras",
@@ -45,12 +45,12 @@ async def client(server):
 
 
 @pytest.mark.asyncio
-async def test_check_models(client: openai.AsyncOpenAI, zephyr_lora_files):
+async def test_check_models(client: openai.AsyncOpenAI, qwen3_lora_files):
     models = await client.models.list()
     models = models.data
     served_model = models[0]
     lora_models = models[1:]
     assert served_model.id == MODEL_NAME
     assert served_model.root == MODEL_NAME
-    assert all(lora_model.root == zephyr_lora_files for lora_model in lora_models)
-    assert lora_models[0].id == "zephyr-lora"
+    assert all(lora_model.root == qwen3_lora_files for lora_model in lora_models)
+    assert lora_models[0].id == "qwen3-lora"