Alternatives to Tiny TPU
200 apps like Tiny TPU, closest match first.
Top picks
- T

tilegym-cutile-python
GetExpert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization.
- T
TrenTorch
LaunchTrenTorch is a set of free machine learning practice problems where you build the core ideas yourself. The main content is 1647 problems, each with a clear explanation, grouped into 12 topics and split into 466 beginner, 633 intermediate an
Open source
- T

tilegym-converting-cutile-to-triton
GetConverts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch,
- R
Rainbow Tensor
LaunchColourful tensor operation visuals for NumPy style arrays, built for notebooks, docs, and teaching shape transformations.
Open source
- T

tilegym-improve-cutile-kernel-perf
GetIteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes,
- M
microgpt
Launchmicrogpt is an interactive visualisation of a very small GPT model that runs in the browser. It is an educational tool for seeing how a language model generates text one character at a time. The model is trained on a dataset of names and le
More like Tiny TPU

gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbar_control_agent segfaults, out-of-memory

tilegym-converting-cutile-to-julia
Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents
Time To First Token
A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization

nemo-mbridge-perf-moe-hardware-configs
Representative, point-in-time MoE training playbooks by hardware

gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources
About Tiny TPU
Tiny TPU
An attempt to understand and build a TPU—by complete novices
Tiny TPU is a write-up of an attempt by four complete novices to understand and build a tensor processing unit, the kind of accelerator Google uses for machine learning. The project is documented as a slideshow with sections on why the team started, what a TPU is, how they developed their toy design, and why they used XOR as a first problem. It walks through batching and dimensions, the systolic array of processing elements that performs matrix multiplication, input and weight scheduling with staggering and FIFOs, bias and leaky ReLU activation, pipelining and double buffering, and a forward pass walkthrough. The authors describe a strict philosophy of trying the hacky way first and consulting outside sources only after, and they say they wrote the code without relying on AI tools.
- Price
- Open source
- Category
- Design
- Website
- tinytpu.com











