Stories by technoabsurdist

Show HN: GPU Profiling That's Useful in 60 Seconds

Show HN: We made PyTorch profiling usable for ML engineers

Chip Benchmark: Hardware-Centric Performance Insights for AI Workloads

ChipBenchmark: Open-Source Benchmarking for LLM Performance Across Hardware

Using AMD MI300X for High-Throughput, Low-Cost LLM Inference

Profile CUDA kernels with one command, zero GPU setup

Show HN: Profile GPU Kernels with One Command, Zero GPU Setup

Show HN: Chisel – Profile GPU Kernels Without a GPU (Nvidia and AMD)

Ask HN: Is anyone using AMD GPUs for their AI workloads?

Show HN: Chisel – GPU development through MCP

Show HN: Chisel – Profile AMD MI300X kernels locally

Show HN: Chisel – AMD GPU development that feels local but runs in the cloud

Crackd – unbiased technical skill comparison among students

Show HN: Molecule-Rs – A Fast Protein Visualization Engine Written in Rust

Show HN: Molecule-Rs – A Fast Protein Visualization Engine Written in Rust

Kojo (The Duolingo for Coding)

YouTube Transcriptions with AI-Generated Summaries

Find Good Podcasts