PyTorchCon North America to feature GPU Kernel Engineering track
PyTorch · x · 2026-09-01
PyTorch announced the #PyTorchCon North America conference, taking place Oct 20-21 in San Jose. The Kernel Engineering track will explore compilers, custom kernels, optimization, and low-level technologies that accelerate AI. Mark Saroufim, co-founder of GPUMODE, will deliver a keynote.
Related event: PyTorch Conference 2026 North America Set for October in San Jose(2 posts)→
More from Infra
- Stop using long-lived AWS credentials; switch to IAM Roles — _jaydeepkarale · 2026-09-01
- llama.cpp Metal optimization boosts IQ3_XXS decode speed on Apple Silicon — predatar · 2026-09-01
- Architecting pipeline-parallel LLM inference across friends' PCs over the internet — BuildWithEren · 2026-09-01
- Building a Private AI OS on 4x RTX 2080 Ti — askincihan · 2026-09-01
- Llama Mac app adds REST API request builder for llama.cpp — ggerganov · 2026-09-01
- DRAM Share in AI Inference Servers to Drop ~40% as Flash Takes Over — AccBalanced · 2026-09-01