What happens after model_running.py loading model weights?

[cduk]

Loading safetensors checkpoint shards: 0% Completed | 0/3 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 33% Completed | 1/3 [00:00<00:01, 1.67it/s]
Loading safetensors checkpoint shards: 67% Completed | 2/3 [00:01<00:00, 1.20it/s]
Loading safetensors checkpoint shards: 100% Completed | 3/3 [00:03<00:00, 1.10s/it]
Loading safetensors checkpoint shards: 100% Completed | 3/3 [00:03<00:00, 1.00s/it]

INFO 11-08 18:02:50 model_runner.py:1025] Loading model weights took 9.5525 GB
INFO 11-08 18:24:45 gpu_executor.py:122] # GPU blocks: 9151, # CPU blocks: 1170

On GPUs where FP16 performance is slow, I notice a large dely in start up between when model's are loaded and the gpu_executor.py message.

Can someone describe what is happening between these 2 steps? I'm trying to figure out where the slow down takes place and see if this can be speeded up somehow.