{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/d2b21f27b80f4107ac90b36c29207646\" frameborder=\"0\" width=\"1664\" height=\"1248\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1248,"width":1664,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1248,"thumbnail_width":1664,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/d2b21f27b80f4107ac90b36c29207646-9fd97f743e56cd30.gif","duration":319.34,"title":"[FEATURE] Modal Runthrough","description":"In this video, I walk you through the process of setting up and running a torch profiling example using our SDK. After generating a basic trace, I demonstrate how to annotate the code to identify the kernels launched during the forward and backward passes. I also explain how to integrate the Encompass SDK for better profiling insights and ensure that user annotations appear directly over the relevant kernels in the timeline. Please follow along and make sure to rerun the modal run after adding the trace points. Your feedback on this process will be invaluable as we refine our approach."}