[Admin maintenance] Support new ZeroGPU hardware

README.md

@@ -4,7 +4,7 @@ emoji: 🔍➡️📝
 colorFrom: gray
 colorTo: green
 sdk: gradio
-sdk_version: 4.44.0
+sdk_version: 5.50.0
 app_file: app.py
 pinned: false
 ---

app.py

@@ -12,13 +12,6 @@ if not hasattr(huggingface_hub, "HfFolder"):
             try: huggingface_hub.logout()
             except Exception: pass
     huggingface_hub.HfFolder = HfFolder
-import subprocess  # 🥲
-
-subprocess.run(
-    "pip install flash-attn --no-build-isolation",
-    env={"FLASH_ATTENTION_SKIP_CUDA_BUILD": "TRUE"},
-    shell=True,
-)
 import spaces
 import gradio as gr
 import re
@@ -36,7 +29,7 @@ os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     "Qwen/Qwen2.5-VL-7B-Instruct",
     torch_dtype=torch.bfloat16,
-    attn_implementation="flash_attention_2",
+    attn_implementation="sdpa",
     device_map="auto",
 )
 processor = AutoProcessor.from_pretrained(