top | item 46178177 (no title) tarruda | 2 months ago > but it’s light years behind on compute.Is that the only factor though? I wonder if pytorch is lacking optimization for the MPS backend. discuss order hn newest rfoo|2 months ago This is the only factor. People sometimes perceive Apple's NPU as "fast" and "amazing" which is simply false.It's just that NVIDIA GPU sucks (relatively) at *single-user* LLM inference and it makes people feel like Apple not so bad.
rfoo|2 months ago This is the only factor. People sometimes perceive Apple's NPU as "fast" and "amazing" which is simply false.It's just that NVIDIA GPU sucks (relatively) at *single-user* LLM inference and it makes people feel like Apple not so bad.
rfoo|2 months ago
It's just that NVIDIA GPU sucks (relatively) at *single-user* LLM inference and it makes people feel like Apple not so bad.