Posts

• Aug 22, 2026

  My Triton From Scratch Part 12: CUDA Tile Layouts

• Aug 15, 2026

  My Triton From Scratch Part 11: Block Factory Functions

• Aug 8, 2026

  My Triton From Scratch Part 10: Runtime For Loops

• Aug 1, 2026

  My Triton From Scratch Part 9: AST Frontend

• Jun 29, 2026

  My Triton From Scratch Part 8: Rank-2 Tiles

• Jun 28, 2026

  My Triton From Scratch Part 7: Minimal MLIR

• Jun 27, 2026

  My Triton From Scratch Part 6: Reductions

• Jun 26, 2026

  My Triton From Scratch Part 5: Verification

• Jun 25, 2026

  My Triton From Scratch Part 4: Elementwise Ops

• Jun 24, 2026

  My Triton From Scratch Part 3: CUDA Lowering

• Jun 23, 2026

  My Triton From Scratch Part 2: Typed SSA

• Jun 22, 2026

  My Triton From Scratch Part 1: Symbolic Tracing

• Apr 30, 2026

  Teaching a LEGO Porsche to Park Itself with Imitation Learning

• Sep 15, 2025

  Inference Server From Scratch - Part 4: KV cache

• Sep 14, 2025

  Inference Server From Scratch - Part 3: Sampling

• Sep 11, 2025

  Inference Server From Scratch - Part 2: Real Model

• Sep 10, 2025

  Inference Server From Scratch - Part 1: OpenAI API

• Jul 29, 2025

  From Tiny Scalar Autograd to Tiny JIT & Tiny AOTAutograd

subscribe via RSS