[1/n][CI] Load models in CI from S3 instead of HF (#13205)

Signed-off-by: <>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>

tests/entrypoints/llm/test_chat.py

@@ -5,12 +5,17 @@ from typing import List
 import pytest
 
 from vllm import LLM
+from vllm.config import LoadFormat
 
+from ...conftest import MODEL_WEIGHTS_S3_BUCKET
 from ..openai.test_vision import TEST_IMAGE_URLS
 
+RUNAI_STREAMER_LOAD_FORMAT = LoadFormat.RUNAI_STREAMER
+
 
 def test_chat():
-    llm = LLM(model="meta-llama/Llama-3.2-1B-Instruct")
+    llm = LLM(model=f"{MODEL_WEIGHTS_S3_BUCKET}/Llama-3.2-1B-Instruct",
+              load_format=RUNAI_STREAMER_LOAD_FORMAT)
 
     prompt1 = "Explain the concept of entropy."
     messages = [
@@ -28,7 +33,8 @@ def test_chat():
 
 
 def test_multi_chat():
-    llm = LLM(model="meta-llama/Llama-3.2-1B-Instruct")
+    llm = LLM(model=f"{MODEL_WEIGHTS_S3_BUCKET}/Llama-3.2-1B-Instruct",
+              load_format=RUNAI_STREAMER_LOAD_FORMAT)
 
     prompt1 = "Explain the concept of entropy."
     prompt2 = "Explain what among us is."
@@ -65,7 +71,8 @@ def test_multi_chat():
                          [[TEST_IMAGE_URLS[0], TEST_IMAGE_URLS[1]]])
 def test_chat_multi_image(image_urls: List[str]):
     llm = LLM(
-        model="microsoft/Phi-3.5-vision-instruct",
+        model=f"{MODEL_WEIGHTS_S3_BUCKET}/Phi-3.5-vision-instruct",
+        load_format=RUNAI_STREAMER_LOAD_FORMAT,
         dtype="bfloat16",
         max_model_len=4096,
         max_num_seqs=5,