Update deprecated Python 3.8 typing (#13971)

examples/offline_inference/vision_language_multi_image.py

@@ -5,7 +5,7 @@ multi-image input on vision language models for text generation,
 using the chat template defined by the model.
 """
 from argparse import Namespace
-from typing import List, NamedTuple, Optional
+from typing import NamedTuple, Optional
 
 from PIL.Image import Image
 from transformers import AutoProcessor, AutoTokenizer
@@ -24,8 +24,8 @@ IMAGE_URLS = [
 class ModelRequestData(NamedTuple):
     llm: LLM
     prompt: str
-    stop_token_ids: Optional[List[int]]
-    image_data: List[Image]
+    stop_token_ids: Optional[list[int]]
+    image_data: list[Image]
     chat_template: Optional[str]
 
 
@@ -34,7 +34,7 @@ class ModelRequestData(NamedTuple):
 # Unless specified, these settings have been tested to work on a single L4.
 
 
-def load_aria(question, image_urls: List[str]) -> ModelRequestData:
+def load_aria(question, image_urls: list[str]) -> ModelRequestData:
     model_name = "rhymes-ai/Aria"
     llm = LLM(model=model_name,
               tokenizer_mode="slow",
@@ -55,7 +55,7 @@ def load_aria(question, image_urls: List[str]) -> ModelRequestData:
     )
 
 
-def load_deepseek_vl2(question: str, image_urls: List[str]):
+def load_deepseek_vl2(question: str, image_urls: list[str]):
     model_name = "deepseek-ai/deepseek-vl2-tiny"
 
     llm = LLM(model=model_name,
@@ -77,7 +77,7 @@ def load_deepseek_vl2(question: str, image_urls: List[str]):
     )
 
 
-def load_h2ovl(question: str, image_urls: List[str]) -> ModelRequestData:
+def load_h2ovl(question: str, image_urls: list[str]) -> ModelRequestData:
     model_name = "h2oai/h2ovl-mississippi-800m"
 
     llm = LLM(
@@ -111,7 +111,7 @@ def load_h2ovl(question: str, image_urls: List[str]) -> ModelRequestData:
     )
 
 
-def load_idefics3(question, image_urls: List[str]) -> ModelRequestData:
+def load_idefics3(question, image_urls: list[str]) -> ModelRequestData:
     model_name = "HuggingFaceM4/Idefics3-8B-Llama3"
 
     # The configuration below has been confirmed to launch on a single L40 GPU.
@@ -142,7 +142,7 @@ def load_idefics3(question, image_urls: List[str]) -> ModelRequestData:
     )
 
 
-def load_internvl(question: str, image_urls: List[str]) -> ModelRequestData:
+def load_internvl(question: str, image_urls: list[str]) -> ModelRequestData:
     model_name = "OpenGVLab/InternVL2-2B"
 
     llm = LLM(
@@ -179,7 +179,7 @@ def load_internvl(question: str, image_urls: List[str]) -> ModelRequestData:
     )
 
 
-def load_mllama(question, image_urls: List[str]) -> ModelRequestData:
+def load_mllama(question, image_urls: list[str]) -> ModelRequestData:
     model_name = "meta-llama/Llama-3.2-11B-Vision-Instruct"
 
     # The configuration below has been confirmed to launch on a single L40 GPU.
@@ -201,7 +201,7 @@ def load_mllama(question, image_urls: List[str]) -> ModelRequestData:
     )
 
 
-def load_nvlm_d(question: str, image_urls: List[str]):
+def load_nvlm_d(question: str, image_urls: list[str]):
     model_name = "nvidia/NVLM-D-72B"
 
     # Adjust this as necessary to fit in GPU
@@ -234,7 +234,7 @@ def load_nvlm_d(question: str, image_urls: List[str]):
     )
 
 
-def load_pixtral_hf(question: str, image_urls: List[str]) -> ModelRequestData:
+def load_pixtral_hf(question: str, image_urls: list[str]) -> ModelRequestData:
     model_name = "mistral-community/pixtral-12b"
 
     # Adjust this as necessary to fit in GPU
@@ -259,7 +259,7 @@ def load_pixtral_hf(question: str, image_urls: List[str]) -> ModelRequestData:
     )
 
 
-def load_phi3v(question: str, image_urls: List[str]) -> ModelRequestData:
+def load_phi3v(question: str, image_urls: list[str]) -> ModelRequestData:
     # num_crops is an override kwarg to the multimodal image processor;
     # For some models, e.g., Phi-3.5-vision-instruct, it is recommended
     # to use 16 for single frame scenarios, and 4 for multi-frame.
@@ -295,7 +295,7 @@ def load_phi3v(question: str, image_urls: List[str]) -> ModelRequestData:
 
 
 def load_qwen_vl_chat(question: str,
-                      image_urls: List[str]) -> ModelRequestData:
+                      image_urls: list[str]) -> ModelRequestData:
     model_name = "Qwen/Qwen-VL-Chat"
     llm = LLM(
         model=model_name,
@@ -336,7 +336,7 @@ def load_qwen_vl_chat(question: str,
     )
 
 
-def load_qwen2_vl(question, image_urls: List[str]) -> ModelRequestData:
+def load_qwen2_vl(question, image_urls: list[str]) -> ModelRequestData:
     try:
         from qwen_vl_utils import process_vision_info
     except ModuleNotFoundError:
@@ -393,7 +393,7 @@ def load_qwen2_vl(question, image_urls: List[str]) -> ModelRequestData:
     )
 
 
-def load_qwen2_5_vl(question, image_urls: List[str]) -> ModelRequestData:
+def load_qwen2_5_vl(question, image_urls: list[str]) -> ModelRequestData:
     try:
         from qwen_vl_utils import process_vision_info
     except ModuleNotFoundError:
@@ -466,7 +466,7 @@ model_example_map = {
 }
 
 
-def run_generate(model, question: str, image_urls: List[str]):
+def run_generate(model, question: str, image_urls: list[str]):
     req_data = model_example_map[model](question, image_urls)
 
     sampling_params = SamplingParams(temperature=0.0,
@@ -487,7 +487,7 @@ def run_generate(model, question: str, image_urls: List[str]):
         print(generated_text)
 
 
-def run_chat(model: str, question: str, image_urls: List[str]):
+def run_chat(model: str, question: str, image_urls: list[str]):
     req_data = model_example_map[model](question, image_urls)
 
     sampling_params = SamplingParams(temperature=0.0,