A new nightly version has been released!
See the quickstart guide for installation instructions: Quickstart | Modular
MAX changelog updates:
- Added support for the Tencent Hunyuan Hy3-preview (
HYV3ForCausalLM)
architecture: a decoder-only mixture-of-experts model (192 routed experts,
top-8 plus one shared expert) with sigmoid plus correction-bias routing,
per-head query/key RMSNorm, and split-half RoPE. Runs multi-GPU with
tensor-parallel attention and expert-parallel MoE.
Mojo changelog updates:
- [mojo-lang] Improve location handling for call errors.
Raw MAX diff: https://github.com/modular/modular/compare/c807ae59ddb6de5bd46241cbfbfb220e0a6fce46...c7c9ceeb261d0b31df83131067f85ef251b14411)>
Current Mojo changelog: https://github.com/modular/modular/blob/main/mojo/docs/nightly-changelog.md