inferencelayer 0.2.7

Kortexya's engine-native inference layer — LLM generation + embedding/encoder family on wgpu (WGSL kernels, any adapter) with a pure-Rust CPU fallback
Documentation
1
2
3
4
5
6
7
Proprietary License

Copyright (c) 2025-2026 Kortexya. All rights reserved.

This software and associated documentation files are the proprietary property
of Kortexya. No part of this software may be reproduced, distributed,
published, or used except with prior written permission from Kortexya.