Видео с ютуба Cuda Inference

Nvidia CUDA in 100 Seconds

Nvidia CUDA vs Apple Metal for AI Work

Запуск ИИ на FreeBSD (проблема CUDA)

Maximize LLM Inference Performance + Auto-Profile/Optimize PyTorch/CUDA Code

What is CUDA? - Computerphile

Оптимизация инференса LLM: асинхронный непрерывный батчинг с использованием CUDA Streams

Writing Code That Runs FAST on a GPU

Analyzing Deepseek's "undefined" NVIDIA PTX optimizations (with benchmarks!)

CUDA Programming Course – High-Performance Computing with GPUs

Освоение оптимизации вывода LLM: от теории до экономически эффективного внедрения: Марк Мойу

Understanding the LLM Inference Workload - Mark Moyou, NVIDIA

Demo - Chatbot Response Acceleration with CUDA LLM Inference

FASTER Inference with Torch TensorRT Deep Learning for Beginners - CPU vs CUDA

Dual RTX 5090s Destroy AI Benchmarks Ollama, CUDA Burn & 34B Model

Must Know Technique in GPU Computing | Episode 4: Tiled Matrix Multiplication in CUDA C

Stillwaters AI - LLM Systems Engineering | Inference, CUDA Memory, Tensor Cores, Observability, HPC