mirror of
https://github.com/hanzoai/ml.git
synced 2026-11-19 23:50:51 +00:00
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]>
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.
Image source: wikimedia.
Pose Estimation
cargo run --example yolo-v8 --release -- \
hanzo-ml-examples/examples/yolo-v8/assets/bike.jpg --task pose
Command-line flags
--which: select the model variant to be used,n,s,m,l, orxby increasing size and quality.--task:detectfor object detection andposefor pose estimation.--legend-size: the size of the characters to print.--model: use a local model file rather than downloading it from the hub.


