How to Beat PyTorch? Writing a Fast MatMul Kernel in Triton - Tensor Cores, L2 Caching & Auto-Tuning
Matrix Multiplication is the heart of every Transformer model. If it's slow, your model is slow. In this episode of Bielik Anatomy, we build a custom MatMul kernel in OpenAI Triton from scratch. Watch as we take a basic implementation and aggressively optimize it—using memory tricks and hardware acceleration—to match PyTorch’s performance on the GPU. Key concepts covered: Writing a basic kernel with tiling and masking Grouped Block Ordering to maximize L2 Cache hits Tensor Cores: Switching to FP16 for massive speedups Auto-Tuning & Pipelining for final polish Timestamps: 0:00 - Why MatMul matters 1:10 - Basic Kernel Implementation 3:25 - Optimization 1: L2 Cache & Grouping 5:03 - Optimization 2: Auto-Tuning 5:49 - Optimization 3: Tensor Cores 6:49 - Optimization 4: Pipeline & Warps 7:25 - Final Benchmark: Matching PyTorch Code & Resources: GitHub Repo: https://github.com/qooba/bielik-anato... Previous Episode: • Bielik LM in Triton - Can I Actually Pull ... #DeepLearning #OpenAITriton #CUDA #BielikAnatomy #GPUOptimization #Bielik

Triton Kernels Actually Work - Here's Proof

JUST FUSE IT: Fixing GPU Memory Bottlenecks with kernel fusion (RMSNorm & Softmax)

Flash Attention vs Standard Attention | 20x Faster in Triton
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
Yann LeCun's $1B Bet Against LLMs [Part 1]

How do Graphics Cards Work? Exploring GPU Architecture

How KV Cache Speeds Up LLMs for Faster AI Models on GPUs

China Is About To Pop The AI Bubble

NVIDIA Tensor Cores Programming

No Boss, No Money: The Raw Reality of China’s Gen-Z Freelancers

Blue gradient background - screensaver, mood lighting, ambiance, TV art, focus, study

THE TRITON LANGUAGE | PHILIPPE TILLET

China’s Sodium Battery Breakthrough Just Made Lithium OBSOLETE

Bielik LM in Triton - Can I Actually Pull This Off?

How is hardware reshaping LLM design?

TV ART SLIDESHOW | Abstract Art for your TV | Jr Korpa | 60 minutes of 4K Paintings

Shor's Algorithm for Quantum Computing - Computerphile

Why the Speed of Light Is NOT a Speed - Leonard Susskind

Creator of C++: Bell Labs, Negative Overhead Abstraction, Mistakes | Bjarne Stroustrup

Implementing RoPE: From Mathematical Formula to Triton Code

