Search Results for "qualcomm"

...AIMET enables neural networks to run more efficiently on fixed-point AI hardware accelerators. Quantized inference is significantly faster than floating point inference. For example, models that we’ve run on the Qualcomm® Hexagon™ DSP rather than on the Qualcomm® Kryo™ CPU have resulted in a 5x to 15x speedup. Plus, an 8-bit model also has a 4x smaller memory footprint relative to a 32-bit model. However, often when quantizing a machine learning model (e.g., from 32-bit floating point to an 8-bit fixed point value), the model accuracy is sacrificed.

...Currently supported vendors are AMD (Linux AMD GPU driver), Apple (limited M1 & M2 support), Huawei (Ascend), Intel (Linux i915 driver), NVIDIA (Linux proprietary divers), and Qualcomm Adreno (Linux MSM driver).

mllm is an open-source inference engine designed to run multimodal large language models efficiently on mobile devices and edge computing environments. The framework focuses on delivering high-performance AI inference in resource-constrained systems such as smartphones, embedded hardware, and lightweight computing platforms. Implemented primarily in C and C++, it is designed to operate with minimal external dependencies while taking advantage of hardware-specific acceleration technologies...

...The main purpose of this project is to bring extra updates to the existing Octave OCL project with more supporting PC devices like Intel GPU, AMD APUs, and Apple Silicon GPU as well as mobile devices like Qualcomm Adreno and ARM Mali GPUs. Due to the fact tremendous time and energy has been spent on its working on many devices, the project name is changing to AnyArray to reflect it is really working on many devices in 9 March 2026. Ever since started providing extra GPU Compute support, it has been for OpenCL-enabled hardware and this promise will not change for OpenSource community. ...

General purpose GPU compute framework built on Vulkan to support 1000s of cross-vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous, and optimized for advanced GPU data processing use cases. Backed by the Linux Foundation.

Instructions: - Be on OOS 13.1.0.581 or .582 firmware with an unlocked bootloader - Have the OnePlus/Qualcomm fastboot and the latest Google ADB Interface drivers installed, along with the latest official Android SDK Platform tools - Download the recovery, boot it with "fastboot boot path/to/recovery.img" - Navigate to adb sideload with the volume keys and press the power button - Run "adb sideload /path/to/aospa.zip" - Wipe data using the volume and power keys if coming from another rom and reboot

Custom Roms, Magisk Modules, Custom Recoverys For The Xiaomi Mi 11 Ultra (star/mars) Specs: -Qualcomm SM8350 (Snapdragon 888) - Ram 8/12/16GB - Storage 128/256/512GB - Battery 5000mAh

Samsung Galaxym51

SmartPlay Technologies project for Yocto build based Linux distribution on InForce(R) SYS6440 platform using the Qualcomm(R) Snapdragon(TM) – APQ8064. Release highlights: · First Yocto build based Linux distro on Qualcomm(R) 8064 reference platform. · Sato UI environment with Poky based Yocto Project 1.5 - Dora. · Based on the Linux Kernel v3.4 from Code Aurora Forum, and proprietary firmware from Inforce(R) SYS6440 Android BSP Rel v1.5 · X11 and Wayland/ Weston 1.4 support · Hardware accelerated graphics using open source Freedreno and Mesa libraries · Hardware video playback using gst-omx on gstreamer 1.0 and libhybris · UI based Audio playback · Wifi using QCA6234x Please refer readme.txt packaged in the release binaries SP_Linux_SYS6440_rls_1.0.0.tar.gz for steps to flash and execute released features. ...

Aiming to pick up shortly after QUALCOMM Eudora 6 for the Mac left off, this project aims to produce, in the short-to-medium term, an advanced POP/IMAP client in C with a Carbon front-end, making it compatible with Intel machines running macOS Mojave and older, and targeting power users first and foremost. Medium-to-long term, it is anticipated that the graphical user interface will be rewritten to leverage Cocoa rather than Carbon, enabling compatibility with post-Mojave Intel machines, and all Apple Silicon (ARM64) machines. ...