Apple Intelligence Foundation Language Models Tech Report 2025(machinelearning.apple.com)

226 points by 2bit 1 year ago | 167 comments

SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators(machinelearning.apple.com)

155 points by pizza 1 year ago | 36 comments

Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents(machinelearning.apple.com)

28 points by CharlesW 8 months ago | 5 comments

Normalizing Flows Are Capable Generative Models(machinelearning.apple.com)

160 points by danboarder 1 year ago | 40 comments

Apple ML Research: Muse Spark Open with MLX on Mac Studio(machinelearning.apple.com)

355 points by antipaul 10 days ago | 188 comments

Apple Machine Learning Research post on running large LLM inference locally and distributed across Mac Studio machines using MLX and RDMA.

NaturalSpeech 2: Zero-shot speech and singing synthesizers(speechresearch.github.io)

206 points by tim_sw 3 years ago | 93 comments

What every developer should know about GPU computing(codeconfessions.substack.com)

422 points by Anon84 3 years ago | 149 comments

A Substack primer by Abhinav Upadhyay explaining GPU architecture and computing concepts for software developers familiar mainly with CPUs.

GPUs Go Brrr(hazyresearch.stanford.edu)

1056 points by nmstoker 2 years ago | 243 comments

Stanford Hazy Research blog post on what GPU hardware wants for efficient AI kernels, introducing the ThunderKittens CUDA kernel library.

Apple's On-Device and Server Foundation Models(machinelearning.apple.com)

890 points by 2bit 2 years ago | 479 comments

Apple Machine Learning Research post introducing the on-device and server foundation language models behind Apple Intelligence.

Nvidia PersonaPlex 7B on Apple Silicon: Full-Duplex Speech-to-Speech in Swift(blog.ivan.digital)

352 points by ipotapov 7 months ago | 113 comments

A Medium blog post on running NVIDIA's PersonaPlex 7B full-duplex speech-to-speech model natively in Swift on Apple Silicon using MLX.

Building Meta's GenAI infrastructure(engineering.fb.com)

636 points by mootpt 2 years ago | 291 comments

Meta engineering blog post describing its large GPU training clusters for generative AI, including RDMA and InfiniBand networking, Grand Teton hardware, and storage.

The GPU, not the TPM, is the root of hardware DRM(mjg59.dreamwidth.org)

399 points by DvdGiessen 1 year ago | 408 comments

Blog post by Matthew Garrett arguing that GPUs, not TPMs, are the real root of hardware DRM; the capture shows a Dreamwidth captcha page instead.