Daniel HiltgenandGitHub 00bef57a9f New model... (#19030) ...

* ci: shorten Windows Vulkan build path

Keep the nested shader-generator compiler probes below Windows path limits in checkouts with longer repository names.

* mlx: fix Nemotron bugs and support global scales

Accept published Nemotron layer names while retaining legacy aliases, and
fix layer-count inference and detached MTP quantization. Stabilize Mamba
softplus, preserve FP32 vision normalization, and compile Mamba gate and
norm scaling.

Support per-expert F32 global scales and preserve activation-scale
companions in ModelOpt and compressed-tensors NVFP4 imports. Normalize
reciprocal globals and reject invalid scales. Keep activation scales
separate from weight-only inference.

* mlx: add Nemotron 3.5 Super

* minor adjustments

2026-10-15 07:28:26 -07:00

..

parsers

parsers: report the strings that end a response's thinking

2026-09-22 11:24:11 -07:00

renderers

New model... (#19030)

2026-10-15 07:28:26 -07:00