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

36 lines
1.0 KiB
TOML

[package]
name = "hanzo-ml-wasm-example-bert"
# Not published: browser demo programs, built and tested in-tree only.
publish = false
version = "0.11.8"
edition = "2021"
description = "Multi-backend tensor & ML framework for Rust — part of the Hanzo ML stack."
repository = "https://github.com/hanzoai/ml"
keywords = ["blas", "tensor", "machine-learning"]
categories = ["science"]
license = "MIT OR Apache-2.0"
[dependencies]
hanzo-ml = { workspace = true }
hanzo-nn = { workspace = true }
hanzo-transformers = { workspace = true }
num-traits = { workspace = true }
tokenizers = { workspace = true, features = ["unstable_wasm"] }
# App crates.
anyhow = { workspace = true }
byteorder = { workspace = true }
log = { workspace = true }
rand = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
safetensors = { workspace = true }
# Wasm specific crates.
console_error_panic_hook = "0.1.7"
getrandom = { version = "0.2", features = ["js"] }
gloo = "0.12"
js-sys = "0.3.64"
wasm-bindgen = "0.2.87"
serde-wasm-bindgen = "0.6.0"