{"href":"https://api.simplecast.com/oembed?url=https%3A%2F%2Fpytorch-dev-podcast.simplecast.com%2Fepisodes%2Ftorchdeploy-Xi5_J1gp","width":444,"version":"1.0","type":"rich","title":"torchdeploy","thumbnail_width":300,"thumbnail_url":"https://image.simplecastcdn.com/images/8cefde76-fb46-406a-8d87-ab0df67f3423/92f11400-2dad-49b4-8b14-cce35f5ab765/pytorch-symbol-02-orangeondark.jpg","thumbnail_height":300,"provider_url":"https://simplecast.com","provider_name":"Simplecast","html":"<iframe src=\"https://player.simplecast.com/1b91c57d-8d99-4434-b75f-cba6420cdd4d\" height=\"200\" width=\"100%\" title=\"torchdeploy\" frameborder=\"0\" scrolling=\"no\"></iframe>","height":200,"description":"torchdeploy is a way of running multiple Python interpreters inside the same process. It can be used to deploy Python PyTorch programs in situations where the GIL is a problem, not the CPython interpreter. How does it work, and what kind of challenges does it pose for people who want to write code that calls from C++ to Python?"}