Files
zeekayandHanzo Dev 6a363f7ee3 merge: upstream main ddf1b879 and the aarch64 repack branch 35d7ae7c
Three-way per file through the rename: base 39355c6c91, theirs the upstream
merge of main with 35d7ae7c (via 7ef6a694d), ours origin/main.

Lands the barrier thread pool, runtime CPU feature dispatch, aarch64 and x86
repacked quantized kernels (indexed_gemv, gemv_fused_shared_lhs), quantized
embedding on CPU/Metal/CUDA, paged flash-attn kernels, cutile fused MoE, the
in-place op aliasing API, parking_lot storage locks, Metal buffer builders and
debug labels, safetensors 0.8, hf-hub 1.0, tokenizers 0.23.

Ours keeps ROCm, Vulkan, wgpu, the IQ/MXFP4/NVFP4/TQ dtypes, and the i-quant
weight/activation block split in matmul. Our backends ride InplaceOpN and the
quantized embedding; Metal get_rows gains the IQ kernels. ug leaves, as upstream.

Co-authored-by: Hanzo Dev <[email protected]>
2026-09-15 15:52:28 -07:00
..
2026-01-16 12:30:55 -08:00

hanzo-ml-yolo-v8: Object Detection and Pose Estimation

This is a port of Ultralytics YOLOv8. The implementation is based on the tinygrad version and on the model architecture described in this issue. The supported tasks are object detection and pose estimation.

You can run this model in your browser via the YOLOv8 WASM example. The model then fully runs in your browser using WebAssembly - if you use a custom image it will never leave your phone/computer!

Running some example

Object Detection

cargo run --example yolo-v8 --release -- hanzo-ml-examples/examples/yolo-v8/assets/bike.jpg

This prints details about the detected objects and generates a bike.pp.jpg file.

Leading group, Giro d'Italia 2021

Image source: wikimedia.

Leading group, Giro d'Italia 2021

Pose Estimation

cargo run --example yolo-v8 --release -- \
  hanzo-ml-examples/examples/yolo-v8/assets/bike.jpg --task pose

Leading group, Giro d'Italia 2021

Command-line flags

  • --which: select the model variant to be used, n, s , m, l, or x by increasing size and quality.
  • --task: detect for object detection and pose for pose estimation.
  • --legend-size: the size of the characters to print.
  • --model: use a local model file rather than downloading it from the hub.