PyTorch Conference to feature Muon optimizer, TorchJD and LLM serving tools from Meta, Google, NVIDIA
PyTorch · x · 2026-09-19
PyTorch teased its North America Conference lineup, focused on training and serving efficiency:
- Optimizers & multi-loss training: sessions on new optimizers like Muon and TorchJD for multi-loss workloads
- Faster LLM serving: tools like fastsafetensors and LMCache for inference and KV-cache efficiency
- Broad speaker roster: engineers from Meta, Google, AWS, Arm, Huawei, IBM, Intel, NVIDIA and Hugging Face, with Meta fielding the largest team including core PyTorch developer Edward Yang
More from Companies & People
- Ex-OpenAI Policy Chief Miles Brundage: It's Not the IPO, It's the IP 'Likely Stolen' — Miles_Brundage · 2026-09-19
- Sarah Hooker: Companies with IP face narrow window to build their own models — josh_wills · 2026-09-19
- AI podcast MOTS marks one year with Taylor Lorenz on AI doom and data center messaging — verdakorzeniews · 2026-09-19
- Matt Shumer: Meta's models 'aren't even in the same league' as Anthropic's — mattshumer_ · 2026-09-19
- AssemblyAI Hosts SF Tech Week Workshop Building Voice Agents Into Vintage Toys — AssemblyAI · 2026-09-19
- Pedro Domingos: OpenAI and Anthropic's real moat is their massive secured compute — pmddomingos · 2026-09-19