Apple Metal
PulseAugur coverage of Apple Metal — every cluster mentioning Apple Metal across labs, papers, and developer communities, ranked by signal.
-
llama.cpp, PyTorch, and new MoE model see significant updates
The llama.cpp project has released updates enhancing WebGPU acceleration and simplifying FlashAttention implementation for more efficient local LLM inference. Concurrently, PyTorch's MPSInductor now supports unsigned in…
-
QuantProof tool automates LLM quantization for task-specific performance
QuantProof is a new tool designed to help users determine the optimal model quantization for their specific tasks. It automates the process of running various models against a user's real-world data, measuring performan…
-
OCaml integrates open-weight LLMs as native functions
A new OCaml library, ocaml-deepseek, has been developed to integrate open-weight LLMs directly into OCaml applications. This library leverages Dwarfstar, a native inference engine, to run models like DeepSeek's V4 Flash…