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-granite LLMs from IBM Research

Granite is a family of Large Language Models built for business, to help drive trust and scalability in AI-driven applications.

Running the example

$ cargo run --example granite --features metal -r -- --model-type "granite7b-instruct" \
    --prompt "Explain how quantum computing differs from classical computing, focusing on key concepts like qubits, superposition, and entanglement. Describe two potential breakthroughs in the fields of drug discovery and cryptography. Offer a convincing argument for why businesses and governments should invest in quantum computing research now, emphasizing its future benefits and the risks of falling behind"

    Explain how quantum computing differs from classical computing, focusing on key concepts like qubits, superposition, and entanglement. Describe two potential breakthroughs in the fields of drug discovery and cryptography. Offer a convincing argument for why businesses and governments should invest in quantum computing research now, emphasizing its future benefits and the risks of falling behind competitors.

    In recent years, there has been significant interest in quantum computing due to its potential to revolutionize various fields, including drug discovery, cryptography, and optimization problems. Quantum computers, which leverage the principles of quantum mechanics, differ fundamentally from classical computers. Here are some of the key differences:

Supported Models

There are two different modalities for the Granite family models: Language and Code.

Granite for language

  1. Granite 7b Instruct