We are a small, specialized software engineering company focused on building secure, high performance systems applications.
© 2026 Micro Perceptron, Inc. All rights reserved. This README is licensed under the CC BY-NC-SA 4.0 license.
We are a small, specialized software engineering company focused on building secure, high performance systems applications.
© 2026 Micro Perceptron, Inc. All rights reserved. This README is licensed under the CC BY-NC-SA 4.0 license.
An MLIR-based toolchain for AMD AI Engine-enabled devices.
Hexagon-MLIR is a compiler toolchain for compiling and executing AI kernels and models on Qualcomm Hexagon Neural Processing Units (NPUs).
Intel® Extension for MLIR. A staging ground for MLIR dialects and tools for Intel devices using the MLIR toolchain.
Transport-neutral, vendor-agnostic virtual accelerator devices. First class cross-platform NPU backend support for Apple, Intel, AMD, Qualcomm devices, as well as Vulkan for cross-platform GPU support.
Unsigned floating-point types for values that can never be negative. Includes custom unsigned binary layouts (e.g. E4M4, E5M3) to unlock an additional mantissa bit, useful for niche cases like mixed-precision graphics and inference.
Modern, advanced, portable, multiprotocol bootloader and boot manager. (Official mirror of https://codeberg.org/Limine/Limine)
This organization has no public members. You must be a member to see who’s a part of this organization.
Loading…
Loading…