Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Repository Index
132,241 visible repositories in the index
1–24 of 27 · Most stars
Translated📚 This repository is a summary of the basic knowledge of recruiting job seekers and beginners in the direction of C/C++ technology, including language, program library, data structure, algorithm, system, network, link loading library, interview experience, recruitment, recommendation, etc.
- interview
- interview-questions
- interview-practice
- interview-preparation
A fast multi-producer, multi-consumer lock-free concurrent queue for C++11
Matter (formerly Project CHIP) creates more connections between more objects, simplifying development for manufacturers and increasing compatibility for consumers, guided by the Connectivity Standards Alliance.
- standard
- internet-of-things
- iot
- chip
2bit quants, kernels and runtime for consumer devices.
TranslatedOffline translation model server with low resource consumption, fast speed, and private deployment capability.
📝 File hashing and checking shell extension
- hash
- hashtab
- checksum
- checksum-calculation
A fast single-producer, single-consumer lock-free queue for C++
Lucebox inference engine for heterogeneous hardware & consumer GPUs
EnergyPlus™ is a whole building energy simulation program that engineers, architects, and researchers use to model both energy consumption and water use in buildings.
A bounded multi-producer multi-consumer concurrent queue written in C++11
- cpp
- cpp11
- header-only
- concurrency
UPnP Media Server for 2026: Stream your digital media through your home network and consume it on all kinds of UPnP supporting devices 📱💻📺
- upnp
- mediaserver
- upnp-av
- cmake
A bounded single-producer single-consumer wait-free and lock-free queue written in C++20
- queue
- concurrency
- concurrent-data-structure
- lock-free
船长关于机器学习、计算机视觉和工程技术的总结和分享
- deep-learning
- computer-vision
- convolutional-neural-networks
- optimization-algorithms
I'm a firm believer that a maintainer should be, at least in some part, a consumer of the thing they're maintaining. I built GGK for a personal project. That project's communication needs have grown considerably, beyond the point where Bluetooth LE is a viable option and I was forced to make the switch to an IP-based solution. As much as I've enjoyed building and using GGK, I no longer have a use-case for Bluetooh LE or a test-case for GGK.
SuMa++: Efficient LiDAR-based Semantic SLAM (Chen et al IROS 2019)
- rangenet-lib
- suma
- lidar
- slam
Complete roadmap for your placement or intern preparation!
- hacktoberfest
- hacktoberfest2021
- placement-preparation
- interview-preparation
Templight is a Clang-based tool to profile the time and memory consumption of template instantiations and to perform interactive debugging sessions to gain introspection into the template instantiation process.
Framework for Enterprise Application Development in c++, HTTP1/HTTP2/HTTP3 compliant, Supports multiple server backends
Monero (XMR) NVIDIA miner
- monero
- xmr
- gpu-mining
- nvidia-miner
E-ink IBM XT clone with solar power, ultra low power consumption, and ultra long battery life.
This Repo consists of Data structures and Algorithms
- recursion
- tree
- array
- linked-list
赛马娘本地化插件「Trainers' Legend G」
- umamusume
llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s over a 100K-token generation at temperature 1 for qwen3.8, supporting full 262K ctx. Supports low memory (12gb) configs for 200k+ ctx. 120+ TPS, 3300+ prefill for QFN 3.8.
- ampere
- consumer-gpu
- cuda
- ggml