malleable computing

By Devine Lu Linvega

Life at the Edge

On fractals of compute and on-device intelligence

On-Device LLM Throughput Calculator - a Hugging Face Space by FL33TW00D-HF

This tool estimates and visualizes the throughput of Large Language Models on devices with memory bandwidth constraints. Users input device and model configurations, and the tool generates a plot s...

Script to set MLX memory limits

Script to set MLX memory limits · GitHub

AI has limits, even if many AI people can't see them

On Ben Recht's fantastic new book

Implementation Divergences · Issue #12 · DavidBuchanan314/millipds

The concrete behaviour of this implementation may diverge from that of the reference impl (that lives in https://github.com/bluesky-social/atproto), sometimes on purpose, sometimes accidentally, so...

. · openai/ten-proofs@d0e1ae7

Lean certificates accompanying proofs in mathematics and theoretical computer science - . · openai/ten-proofs@d0e1ae7

The Complete Power Automate Functions List - Matthew Devaney

A cheat sheet with 140+ Power Automate functions, links to the official documentation and an easy to follow visual guide.

LLMs Can Now Write GPU Kernels That Beat torch.compile - Break AI Scaling Limits in 7 Days

We're now seeing multi-agent systems that take your PyTorch code and produce CUDA or Triton kernels with 2x to 14x speedups over torch.compile(mode='max-autotune-no-cudagraphs'). Not on toy benchmarks. On real models like Llama-3.1-8B, Whisper, and Stable Diffusion. Learn proven techniques to shift the scaling law intercept and achieve 10-50% performance gains.

. · openai/ten-proofs@5a102c1

Lean certificates accompanying proofs in mathematics and theoretical computer science - . · openai/ten-proofs@5a102c1

. · openai/ten-proofs@94bc0fe

Lean certificates accompanying proofs in mathematics and theoretical computer science - . · openai/ten-proofs@94bc0fe

LIMITS 2025 -- Workshop on Computing within Limits

The LIMITS workshop concerns the role of computing in human societies situated in a world of limits, such as limits of extractive logics, limits to a biosphere’s ability to recover, limits to our knowledge, or limits to technological solutions to societal issues. As an interdisciplinary group of researchers, practitioners, and scholars, we seek to reshape the computing research agenda, grounded by an awareness that contemporary computing research is intertwined with ecological limits in general, and climate- and climate justice-related limits in particular. LIMITS 2025 solicits submissions that move us closer towards computing that supports diverse human and non-human lifeforms and thriving biospheres.

. · openai/ten-proofs@e9dce9a

Lean certificates accompanying proofs in mathematics and theoretical computer science - . · openai/ten-proofs@e9dce9a

FunctionGemma: Bringing bespoke function calling to the edge

FunctionGemma is a specialized version of our Gemma 3 270M model fine-tuned for function calling.