Apple introduces M4 chip

Re:Apple introduces M4 chip by teaearlgraycold on Tuesday May 07, 2024 @02:48PM (#40289907)

Pytorch actually has surprisingly good support for Apple Silicon. Occasionally an operation needs to use CPU fallback but many applications are able to run inference entirely off of the CPU cores.

[ Parent | on HN ]

Re:Apple introduces M4 chip by ein0p on Tuesday May 07, 2024 @03:09PM (#40290198)

I’ve found it to be pretty terrible compared to CUDA, especially with Huggingface transformers. There’s no technical reason why it has to be terrible there though. Apple should fix that.

[ Parent | on HN ]

Re:Apple introduces M4 chip by teaearlgraycold on Tuesday May 07, 2024 @07:17PM (#40292619)

Yeah. It’s good with YOLO and Dino though. My M2 Max can compute Dino embeddings faster than a T4 (which is the GPU in AWS’s g4dn instance type).

[ Parent | on HN ]

Re:Apple introduces M4 chip by ein0p on Tuesday May 07, 2024 @07:37PM (#40292759)

MLX will probably be even faster than that, if the model is already ported. Faster startup time too. That’s my main pet peeve though: there’s no technical reason why PyTorch couldn’t be just as good. It’s just underfunding and neglect

[ Parent | on HN ]

Re:Apple introduces M4 chip by whimsicalism on Tuesday May 07, 2024 @09:40PM (#40293518)

t4's are like 6 years old

[ Parent | on HN ]

Re:Apple introduces M4 chip by rcarmo on Tuesday May 07, 2024 @03:08PM (#40290175)

And there is a lot of work being done with mlx.

[ Parent | on HN ]