NVIDIA brings 12 talks on FP4 quantization, robotics to PyTorch Conference 2026
PyTorch · x · 2026-10-15
PyTorch announced NVIDIA's sponsor lineup for PyTorch Conference North America 2026 (Oct 20-21, San Jose): 12 talks and 25 posters covering compiler & CUDA Graphs (dynamic shapes, MoE training, Inductor-TV), low-precision training (FP4 quantization, FP8 multimodal, NVFP4 pretraining), distributed systems (Symmetric Memory, elastic expert parallelism in vLLM, NCCL Shrink & Revoke), and physical/agentic AI (World Action Model, multi-teacher distillation, closed-loop robotics evals). Engineers will present and take questions.
Related event: PyTorch Conference North America Set for San Jose with 12 NVIDIA Talks(3 posts)→
More from Infra
- a16z chart: old GPUs are appreciating assets as B200 rental hits $5.69/hour amid compute scarcity — a16z · 2026-10-15
- 1GW of Compute Matches the Gross Profit of 1M Cybercabs — SpaceX to Add 3-5GW Next Year — JOBhakdi · 2026-10-15
- Cloudflare data: Yandex outage didn't kill malicious bots, they just moved to other Russian hosts — Cloudflare Blog · 2026-10-15
- AI cost falling 54x faster than electricity ever did, five years in — LinusEkenstam · 2026-10-15
- Inference has no yardstick: 4.5-quadrillion token run rate, but no proof of what buyers get — AccBalanced · 2026-10-15
- Booming business, falling stocks: scarcity caps ASML and Applied Materials upside — TiernanRayTech · 2026-10-15