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-quantized-qwen2-instruct

Qwen2 is an upgraded version of Qwen1.5, released by Alibaba Cloud.

Running the example

cargo run --example quantized-qwen2-instruct --release -- --prompt "Write a function to count prime numbers up to N."

0.5b, 1.5b, 7b and 72b models are available via --which argument.

 cargo run --release --example quantized-qwen2-instruct --   --which 0.5b   --prompt "Write a function to count prime numbers up to N."