A new nightly version has been released! ![]()
See the quickstart guide for installation instructions: Quickstart | Modular
MAX changelog updates:
- Extended Nemotron-H with the Nemotron-3-Nano-30B-A3B hybrid MoE variant (a
sigmoid-plus-bias top-6 router over 128 routed experts plus a shared expert)
and enabled the Nemotron-H architecture on Apple silicon GPUs in bfloat16.
The MoE path on Metal uses an integer-domain expert-gather index
(ops.floor_div, avoiding a 64-bit-float divide) and a 32-bit
moe_create_indicesatomic (Apple GPUs lack 64-bit atomics), and adds an
Apple FP4 (W4A16) decode GEMV with an f16-domain E2M1 decode plus a
redesigned varlen causal-conv1d kernel. Verified on M5: the 30B-A3B MoE
serves in bfloat16 at GSM8K 8-shot ~0.85.
Mojo changelog updates:
- [mojo-lang] polish: Make
@explicit_destroyused only for setting error message
Raw MAX diff: https://github.com/modular/modular/compare/d88cd44bcc2148d27f7bea17e8de98855dc17ce6...e06d9d47bf1cecad786afd95faad859a2539bc67)>
Current Mojo changelog: https://github.com/modular/modular/blob/main/mojo/docs/nightly-changelog.md