Stories by matt_d

Making the Clang AST Leaner and Faster

Draw high dimensional tensors as a matrix of matrices

Wafer-Scale AI Compute: A System Software Perspective

Towards Automated GPU Kernel Generation

Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs

Triton Developer Conference 2025 Talks [video]

OpenEstimate Evaluating LLMs on Reasoning Under Uncertainty with Real-World Data

torchcomms: A modern PyTorch communications API

Building an Open ABI and FFI for ML Systems

Instruction Set Migration at Warehouse Scale

Secure Parsing and Serializing with Separation Logic Applied to CBOR, CDDL, COSE [pdf]

The Calculated Typer – Haskell Symposium (ICFP⧸SPLASH'25) [video]

PickleBall: Secure Deserialization of Pickle-Based Machine Learning Models

Clang Bytecode Interpreter Update

Scaling Instruction-Selection Verification Against Authoritative ISA Semantics

10 Myths of Scalable Parallel Languages Part 7: Minimalist Language Designs

CPU Autoscaling with a Kernel of Truth

SafeRace: WebGPU Memory Safety in the Presence of Data Races

A guided tour through Oxidized OCaml

Functional Networking for Millions of Docker Desktops (Experience Report)

1
2
3
4
5
6
7
8
9
10