mirror of
https://github.com/hanzoai/ml.git
synced 2026-11-20 22:12:15 +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-quantized-gemma
ML implementation of quantized Gemma.
Running an example
$ cargo run --example quantized-gemma -- --prompt "Write a function to calculate fibonacci numbers. "
> ```python
> def fibonacci(n):
> """Calculates the nth Fibonacci number using recursion."""
> if n <= 1:
> return n
> else:
> return fibonacci(n-1) + fibonacci(n-2
> ```