20:34How LLMs survive in low precision | Quantization FundamentalsJulia Turc56.0K viewsView & Download
19:48LoRA, QLoRA & 4-Bit Quantization Explained | NF4 & Hand-Calculated Memory Math (Under 20 Min)SPARSH ANALYTICS67 viewsView & Download
18:52Audio Overview: FP4 All the Way: Fully Quantized Training of LLMsXiao Yang89 viewsView & Download
33:55Be Top 0.1% - 4x LLM Training Speed - FP4 of LLMs (Pretraining, Inference)Vuk Rosić354 viewsView & Download
15:404-Bit Training for Billion-Parameter LLMs? Yes, Really.AI Coffee Break with Letitia14.7K viewsView & Download
8:32[QA] Optimizing Large Language Model Training Using FP4 QuantizationArxiv Papers64 viewsView & Download
19:46Quantization vs Pruning vs Distillation: Optimizing NNs for InferenceEfficient NLP65.4K viewsView & Download
8:16The 4-Bit Revolution: FP4 Training, NVFP4 vs MXFP4, and Nvidia Blackwell ExplainedFranksWorld of AI1.5K viewsView & Download
52:19Zhiyu Cheng (NVIDIA) FP4 quantization and its real-world applications on LLMs and diffusion modelsIDEAL27 viewsView & Download
11:48Why NVIDIA NVFP4 is Most Efficient in 4 Bit LLM Training | NVIDIA's New Innovation | Tech Edge AITech Edge AI-ML428 viewsView & Download