About 6 results for "UCtAcpQcYerN8xxZJYTfWBMw"

Featured Results

PT1H19M37S

Paper: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Umar JamilJan 21, 2025

60k

PT7H38M18S

Flash Attention derived and coded from first principles with Triton (Python)

Umar JamilNov 13, 2024

70k

PT1H14M29S

Mamba and S4 Explained: Architecture, Parallel Scan, Kernel Fusion, Recurrent, Convolution, Math

Umar JamilJan 7, 2024

57k

PT1H26M21S

Mistral / Mixtral Explained: Sliding Window Attention, Sparse Mixture of Experts, Rolling Buffer

Umar JamilDec 27, 2023

39k

PT21M12S

How diffusion models work - explanation and code!

Umar JamilDec 19, 2023

30k

PT50M55S

Quantization explained with PyTorch - Post-Training Quantization, Quantization-Aware Training

Umar JamilDec 18, 2023

47k