Post from Nov 05, 2025
This post concludes (for now) my ongoing deep-dive into ML compilers, while researching for sdkit v3. I've linked (at the end) to some of the papers that I read related to graph execution on GPUs.
Blog¶
Post from Oct 27, 2025
A possible intuition for understanding GPU memory hierarchy (and the performance penalty for data transfer between various layers) is to think of it like a manufacturing logistics problem:
- CPU (host) to GPU (device) is like travelling overnight between two cities. The CPU city is like the "headquarters", and contains a mega-sized warehouse of parts (think football field sizes), also known as 'Host memory'.
- Each GPU is like a different city, containing its own warehouse outside the city, also known as 'Global Memory'. This warehouse stockpiles whatever it needs from the headquarters city (CPU).
- Each SM/Core/Tile is a factory located in different areas of the city. Each factory contains a small warehouse for stockpiling whatever inventory it needs, also known as 'Shared Memory'.
- Each warp is a bulk stamping machine inside the factory, producing 32 items in one shot. There's a tray next to each machine, also known as 'Registers'. This tray is used for keeping stuff temporarily for each stamping process.
Post from Oct 24, 2025
Good post on using MLIR for compiling ML models to GPUs. It gives a good broad overview of a GPU architecture, and how MLIR fits into that. The overall series looks pretty interesting too!
Post from Oct 22, 2025
Wrote a fresh implementation of most of the popular samplers and schedulers used for image generation (Stable Diffusion and Flux) at https://github.com/cmdr2/samplers.cpp. A few other schedulers (like Align Your Steps) have been left out for now, but are pretty easy to implement.
Post from Oct 10, 2025
Some notes on machine-learning compilers, gathered while researching tech for Easy Diffusion's next engine (i.e. sdkit v3). For context, see the design constraints of the new engine.
Post from Oct 10, 2025
The design constraints for Easy Diffusion's next engine (i.e. sdkit v3) are:
- Lean: Install size of < 200 MB uncompressed (excluding models).
- Fast: Performance within 10% of the best-possible speed on that GPU for that model.
- Capable: Supports Stable Diffusion 1.x, 2.x, 3.x, XL, Flux, Chroma, ControlNet, LORA, Embedding, VAE. Supports loading custom model weights (from civitai etc), and memory offloading (for smaller GPUs).
- Targets: Desktops and Laptops, Windows/Linux/Mac, NVIDIA/AMD/Intel/Apple.
Post from Sep 01, 2025
Cleared the backlog of stale issues on ED's github repo. This brought down the number of open issues from ~350 to 74.
Post from Aug 25, 2025
Experimented with TensorRT-RTX (a new library offered by NVIDIA).
Post from Jun 17, 2025
Development update for Easy Diffusion - It's chugging along in starts and stops. Broadly, there are three tracks:
Post from Mar 04, 2025
Upgraded the default version of Easy Diffusion to Python 3.9. Newer versions of torch don't support Python 3.8, so this became urgent after the release of NVIDIA's 50xx series GPUs.