add virtual mem logging

handler.py

@@ -246,36 +246,64 @@ class EndpointHandler():
         logging.set_verbosity_info()
         logger = logging.get_logger("transformers")
         logger.info(f"CPU Usage before models loaded: {cpu_percent}%")
+        mem_info = psutil.virtual_memory()
+        used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
+        total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
+        logger.info(f"Used Memory before models loaded: {used_mem:.2f} GB, Total RAM: {total_mem:.2f} GB")
         # Uptake
         uptake_model = UptakeModel(
             self.device, self.tokenizer, self.input_builder)
         uptake_model.run_inference(transcript, min_prev_words=params['uptake_min_num_words'],
                                    uptake_speaker=params.pop("uptake_speaker", None))
         cpu_percent = psutil.cpu_percent()
+        mem_info = psutil.virtual_memory()
+        used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
+        total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
+        logger.info(f"Used Memory after model 1 loaded: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
         logger.info(f"CPU Usage after model 1 loaded: {cpu_percent}%")
         del uptake_model
         cpu_percent = psutil.cpu_percent()
+        mem_info = psutil.virtual_memory()
+        used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
+        total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
+        logger.info(f"Used Memory after model 1 deleted: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
         logger.info(f"CPU Usage after model 1 deleted: {cpu_percent}%")
         # Reasoning
         reasoning_model = ReasoningModel(
             self.device, self.tokenizer, self.input_builder)
         reasoning_model.run_inference(transcript)
         cpu_percent = psutil.cpu_percent()
+        mem_info = psutil.virtual_memory()
+        used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
+        total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
+        logger.info(f"Used Memory after model 2 loaded: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
         logger.info(f"CPU Usage after model 2 loaded: {cpu_percent}%")
-        print(f"CPU Usage after model 2 loaded: {cpu_percent}%")
+        # print(f"CPU Usage after model 2 loaded: {cpu_percent}%")
         del reasoning_model
         cpu_percent = psutil.cpu_percent()
+        mem_info = psutil.virtual_memory()
+        used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
+        total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
+        logger.info(f"Used Memory after model 2 deleted: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
         logger.info(f"CPU Usage after model 2 deleted: {cpu_percent}%")
-        print(f"CPU Usage after model 2 deleted: {cpu_percent}%")
+        # print(f"CPU Usage after model 2 deleted: {cpu_percent}%")
         # Question
         question_model = QuestionModel(
             self.device, self.tokenizer, self.input_builder)
         question_model.run_inference(transcript)
         cpu_percent = psutil.cpu_percent()
         logger.info(f"CPU Usage after model 3 loaded: {cpu_percent}%")
-        print(f"CPU Usage after model 3 loaded: {cpu_percent}%")
+        mem_info = psutil.virtual_memory()
+        used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
+        total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
+        logger.info(f"Used Memory after model 3 loaded: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
+        # print(f"CPU Usage after model 3 loaded: {cpu_percent}%")
         del question_model
         cpu_percent = psutil.cpu_percent()
         logger.info(f"CPU Usage after model 3 deleted: {cpu_percent}%")
-        print(f"CPU Usage after model 3 deleted: {cpu_percent}%")
+        mem_info = psutil.virtual_memory()
+        used_mem = mem_info.used / (1024 ** 3)  # Convert to gigabytes
+        total_mem = mem_info.total / (1024 ** 3)  # Convert to gigabytes
+        logger.info(f"Used Memory after model 3 deleted: {used_mem:.2f} GB, Total Mem: {total_mem:.2f} GB")
+        # print(f"CPU Usage after model 3 deleted: {cpu_percent}%")
         return transcript.to_dict()