GPUs Go Brrr (via) Fascinating, detailed low-level notes on how to get the most out of NVIDIA's H100 GPUs (currently selling for around $40,000 a piece) from the research team at Stanford who created FlashAttention, among other things.
The swizzled memory layouts are flat-out incorrectly documented, which took considerable time for us to figure out.
Recent articles
- Claude Skills are awesome, maybe a bigger deal than MCP - 16th October 2025
- NVIDIA DGX Spark: great hardware, early days for the ecosystem - 14th October 2025
- Claude can write complete Datasette plugins now - 8th October 2025