llama.cpp fork: custom radix-select top-k kernel + CUDA graphs for prefill for fast prompt processing
☆11Aug 16, 2026Updated 2 months ago
Alternatives and similar repositories for working_ds4_speed
Users that are interested in working_ds4_speed are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- WriteOnSide, a "Sidenote" app for Windows.☆15Aug 25, 2026Updated 2 months ago
- Coding agent with cool features.☆19Aug 23, 2026Updated 2 months ago
- Examples of using the OpenAI Responses API with the openai-go package☆16May 14, 2025Updated last year
- Collection of tools for ROSE Online☆18Nov 19, 2021Updated 4 years ago
- Zaxy turns agent work into durable, auditable memory: a hash-chained Eventloom log as the source of truth, an embedded temporal knowledge…☆17Aug 10, 2026Updated 2 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- A simple Windows Azure Cloud Service to demonstrate how one can build a "Task Scheduler" service in Windows Azure☆14Jan 24, 2013Updated 13 years ago
- Instruments wasm files and traces execution☆32Mar 15, 2021Updated 5 years ago
- VecoLuc is a scalable vector search engine that leverages Apache Lucene and the JDK's incubator vector API for high-performance vector op…☆11Aug 22, 2024Updated 2 years ago
- "Functional Java by Example" articles, which you can find on my blog.☆11Nov 30, 2019Updated 6 years ago
- Documentation of an effort to reverse engineer a Cisco 2501 router, with the end goal to run my own code on it (in particular FreeRTOS)☆31Sep 19, 2026Updated last month
- Ngent wraps command-line agents that speak the Agent Client Protocol (ACP) into a web service, making them accessible via HTTP API and We…☆33Jun 21, 2026Updated 4 months ago
- Multi-GPU prefill acceleration for llama.cpp☆15Oct 23, 2026Updated 2 weeks ago
- Provides annotations to use in your .NET Web API 2+ controllers to help with versioning☆13Jan 15, 2016Updated 10 years ago
- Qwen3.8-27B on one DGX Spark (TensorFold)☆42Oct 1, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A small sample showcasing interaction with the Microsoft Band☆13Feb 24, 2015Updated 11 years ago
- Personal tuning for the LXQt desktop to make it more beautiful.☆11Oct 30, 2022Updated 4 years ago
- Provides AclService and MutableAclService implementations that enable usage of Spring Security ACLs with an Apache Cassandra database.☆11Sep 14, 2014Updated 12 years ago
- A complete EFI for Hackintosh, running the latest version of OpenCore and macOS for Lenovo ThinkCentre M720q☆11Nov 22, 2021Updated 4 years ago
- A Streamlit web application to manage and automate GitHub Copilot development workflows☆16Jan 22, 2026Updated 9 months ago
- Build monitor for TeamCity written in Scala☆14Sep 20, 2018Updated 8 years ago
- challenge☆23Apr 6, 2026Updated 7 months ago
- 21Summer-VE370-Intro-to-Computer-Organization-Projects: -Project1: RISC-V Assembly, simluating c code. -Project2: 1.RISC-V64 sin…☆15Apr 11, 2023Updated 3 years ago
- While we are waiting for the official translation from MangaGamer, why not translate the game with ChatGPT?☆21Oct 4, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Kingroon KP5L Marlin Firmware☆14Sep 9, 2024Updated 2 years ago
- ☆11Jun 27, 2025Updated last year
- Azure Container Instances Module☆19Nov 28, 2022Updated 3 years ago
- Intelligent Volleyball posture recognition and correction☆12Nov 18, 2025Updated 11 months ago
- ☆11Apr 13, 2021Updated 5 years ago
- Patches to the standard Nook libraries☆15May 31, 2013Updated 13 years ago
- ☆10Jun 7, 2022Updated 4 years ago
- Empirical benchmarks and quality evaluations of Qwen3.8-27B with Multi-Token Prediction (MTP) across Splash, MTPLX, MLX, and llama.cpp on…☆21Sep 21, 2026Updated last month
- 🌑 Headless PKM server that turns any note folder into a programmable platform. Works with Obsidian, Logseq, and Zim out of the box. Zero…☆17Mar 24, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Build Monitor for TeamCity using TeamCitysharp☆20Oct 31, 2012Updated 14 years ago
- ☆20Aug 7, 2026Updated 3 months ago
- A Serilog sink that writes log events to WinUI 3 collection controls like the ItemsRepeater.☆20Jun 5, 2022Updated 4 years ago
- Fluxbox, but for Wayland, agentically built with Claude☆17Oct 27, 2026Updated last week
- OSX and Ubuntu phonetic Russian keyboards on Windows☆15Mar 23, 2020Updated 6 years ago
- Dynamic visual-response skill for OpenCode☆31Jul 23, 2026Updated 3 months ago
- Roslyn Analyzer to detect privacy-compromised dependencies.☆23Aug 11, 2023Updated 3 years ago