kb
@keighbee.bsky.social
Machine Learning Engineer @ HuggingFace
🕯️🔥[Candle](github.com/huggingface/...) is now much faster on macOS thanks to a contribution by @EricLBuehler, which brings major speed improvements to the Metal backend.🍎📈
Try it out by running some of our examples with the `--features metal` flag.
#Candle #RustLang #macOS #Metal #HuggingFace
Try it out by running some of our examples with the `--features metal` flag.
#Candle #RustLang #macOS #Metal #HuggingFace
July 21, 2025 at 10:22 PM
🕯️🔥[Candle](github.com/huggingface/...) is now much faster on macOS thanks to a contribution by @EricLBuehler, which brings major speed improvements to the Metal backend.🍎📈
Try it out by running some of our examples with the `--features metal` flag.
#Candle #RustLang #macOS #Metal #HuggingFace
Try it out by running some of our examples with the `--features metal` flag.
#Candle #RustLang #macOS #Metal #HuggingFace
Preliminary data shows the Apple Neural Engine uses ~94% less energy than the CPU and ~75% less than the GPU 🤯
On the On-Device team at Hugging Face, we've been profiling energy usage for CoreML models. Here’s some data I collected:
On the On-Device team at Hugging Face, we've been profiling energy usage for CoreML models. Here’s some data I collected:
December 5, 2024 at 8:08 PM
Preliminary data shows the Apple Neural Engine uses ~94% less energy than the CPU and ~75% less than the GPU 🤯
On the On-Device team at Hugging Face, we've been profiling energy usage for CoreML models. Here’s some data I collected:
On the On-Device team at Hugging Face, we've been profiling energy usage for CoreML models. Here’s some data I collected: