Tokenless

Quantization

You Might Not Need 50 Diffusion Steps — Ziv Ilan, Nvidia

You Might Not Need 50 Diffusion Steps — Ziv Ilan, Nvidia

Ziv Ilan from NVIDIA details how latency in video diffusion models can be drastically reduced to achieve real-time generation. He presents a layered approach combining dynamic quantization for memory and speed, chunk-based caching to skip redundant denoising computations, and, most critically, step distillation—training models to achieve high-quality output in significantly fewer steps. These techniques, packaged in the open-source FastGen repository, offer additive performance gains, enabling real-time video on a single Blackwell B200 GPU.

The Future of AI – Key Trends Shaping What’s Next • Ekaterina Sirazitdinova • YOW! 2025

The Future of AI – Key Trends Shaping What’s Next • Ekaterina Sirazitdinova • YOW! 2025

Ekaterina Sirazitdinova from NVIDIA provides a high-level overview of the latest trends shaping the future of AI, covering the evolution from early deep learning to the rise of agentic and physical AI, and diving deep into the critical optimization techniques required to deploy these powerful models efficiently.

Running LLMs on your iPhone: 40 tok/s Gemma 4 with MLX — Adrien Grondin, Locally AI

Running LLMs on your iPhone: 40 tok/s Gemma 4 with MLX — Adrien Grondin, Locally AI

Adria Grondin, developer of the Locally AI app, provides a technical walkthrough on running large language models like Google's Gemma on an iPhone using Apple's MLX framework. The talk covers the necessary tools, performance expectations, the importance of quantization, and the growing MLX ecosystem.

LLM Compression Explained: Build Faster, Efficient AI Models

LLM Compression Explained: Build Faster, Efficient AI Models

Learn how AI model compression and quantization techniques are essential for optimizing Large Language Model (LLM) performance and significantly reducing inference costs in production. This deep dive covers practical examples, benefits like reduced latency and increased throughput, and strategies for different AI use cases, demonstrating how to deploy scalable AI with minimal accuracy degradation.

Quantized LLM Training at Scale with ZeRO++ // Guanhua Wang // AI in Production 2025

Quantized LLM Training at Scale with ZeRO++ // Guanhua Wang // AI in Production 2025

Guanhua Wang from Microsoft's DeepSpeed team explains ZeRO++, a system that tackles the communication bottleneck in large-scale LLM training. By quantizing weights and gradients, ZeRO++ reduces communication volume by 4x, leading to training speedups of over 2x, particularly in low-bandwidth and small-batch-size environments.