use fp8 version of qwen3 30ba3b & 32b

app.py

@@ -24,8 +24,8 @@ cancel_event = threading.Event()
 # Torch-Compatible Model Definitions with Adjusted Descriptions
 # ------------------------------
 MODELS = {
-    "QuixiAI/Qwen3-30B-A3B-AWQ": {"repo_id": "QuixiAI/Qwen3-30B-A3B-AWQ", "description": "QuixiAI/Qwen3-30B-A3B-AWQ"},
-    "Qwen/Qwen3-32B-AWQ": {"repo_id": "Qwen/Qwen3-32B-AWQ", "description": "Qwen/Qwen3-32B-AWQ"},
+    "Qwen/Qwen3-30B-A3B-FP8": {"repo_id": "Qwen/Qwen3-30B-A3B-FP8", "description": "Qwen/Qwen3-30B-A3B-FP8"},
+    "Qwen/Qwen3-32B-FP8": {"repo_id": "Qwen/Qwen3-32B-FP8", "description": "Qwen/Qwen3-32B-FP8"},
     "DeepSeek-R1-0528-Qwen3-8B": {"repo_id": "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B", "description": "DeepSeek-R1-0528-Qwen3-8B"},
     "Nemotron-Research-Reasoning-Qwen-1.5B": {"repo_id": "nvidia/Nemotron-Research-Reasoning-Qwen-1.5B", "description": "Nemotron-Research-Reasoning-Qwen-1.5B"},
     "Qwen2.5-Taiwan-1.5B-Instruct": {"repo_id": "benchang1110/Qwen2.5-Taiwan-1.5B-Instruct", "description": "Qwen2.5-Taiwan-1.5B-Instruct"},