KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM
- ggml
- kv-cache
- llama-cpp
- llm-inference
142,273 visible repositories in the index
121–144 of 277 · Most stars
KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM
DeepRec is a high-performance recommendation deep learning framework based on TensorFlow. It is hosted in incubation in LF AI & Data Foundation.
Manage filesystem snapshots and allow undo of system modifications
A tool which allows you to edit source code of any MSVC C++ project live at runtime
Free EXR file viewer. DJV is a free, open-source high bit-depth image sequence player built for professional film, VFX & animation workflows. Use it for frame-accurate dailies, shot review, and A/B comparisons. Available for Linux, macOS, and Windows.
Samples for Intel® oneAPI Toolkits
Human Pose estimation with TensorFlow framework
The fastest RVA23 RISC-V sandbox
Baidu Bigflow is an interface that allows for writing distributed computing programs and provides lots of simple, flexible, powerful APIs. Using Bigflow, you can easily handle data of any scale. Bigflow processes 4P+ data inside Baidu and runs about 10k jobs every day.
A lightweight header-only library for using Keras (TensorFlow) models in C++.
Samples and Tools for Windows ML.
Async Loading Screen is a free and open-source plugin for Unreal Engine. Async Loading Screen allows you to easily configure a Loading Screen System in the project settings, and automatically add a Loading Screen whenever you open a new level, without Level Streaming.
A tool for Windows to copy text from dialogs and controls which don't allow it otherwise
Nintendo Switch sysmodule that allows support for third-party controllers
High performance components for building Trading Platform such as ultra fast matching engine, order book processor
RTBkit is an open-source software package that allows you to create and deploy a Real Time Bidder for display advertising.
A LLVM-based static analysis framework.
P1031 low level file i/o and filesystem library for the C++ standard
fmtlog is a performant fmtlib-style logging library with latency in nanoseconds.
A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario
LYNX SHARE — lightweight open-source DAW in C++20/JUCE with the FL Studio workflow: Channel Rack, Piano Roll, Playlist, Mixer and .flp import
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
:dancer: Real-time single person pose estimation for Android and iOS.
This is the fully-functional GNU Radio software-defined radio (SDR) implementation of a LoRa transceiver with all the necessary receiver components to operate correctly even at very low SNRs. This work has been conducted at the Telecommunication Circuits Laboratory, EPFL.