Compressed KV cache as cross-backend wire format for Metal + CUDA split inference over Thunderbolt 5
☆16Apr 14, 2026Updated 3 months ago
Alternatives and similar repositories for turboquant-tinygrad-bridge
Users that are interested in turboquant-tinygrad-bridge are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆24Mar 26, 2026Updated 4 months ago
- Run a 35B MoE model at 10+ tok/s on a $600 Mac mini. Pure C/Metal inference engine streaming experts from SSD on Apple Silicon☆19Apr 20, 2026Updated 3 months ago
- Chatons is a desktop AI workspace for coding and project workflows: it lets you chat with multiple AI providers, pick scoped or full mod…☆18May 27, 2026Updated 2 months ago
- LLM inference in C/C++☆35Apr 12, 2026Updated 3 months ago
- ☆10Jun 16, 2025Updated last year
- 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.
- Fork of turbo quant tom-tom and TurboQuant KV cache from domwox☆30Jul 7, 2026Updated last month
- ☆13Feb 8, 2023Updated 3 years ago
- A NERDTree-style sidebar for managing Claude Code sessions in tmux☆15Feb 26, 2026Updated 5 months ago
- Curated AMD GPU compatibility index and CLI for AI workloads☆31May 23, 2026Updated 2 months ago
- Install the ComfyUI Cloud MCP server for Claude, Cursor, and other AI agents☆18Jun 22, 2026Updated last month
- Publicly available code for Net Protocol☆15Jul 23, 2026Updated 2 weeks ago
- ☆12Jul 9, 2020Updated 6 years ago
- Pairwise theory based test cases generator☆13Jun 7, 2021Updated 5 years ago
- ANE (Apple Neural Engine) CostModel profiler for CoreML models☆36Apr 9, 2026Updated 4 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- AI skills for Claude Code. Product marketing, strategy & GTM frameworks by a product leader and full-stack builder in the age of AI.☆20Feb 7, 2026Updated 6 months ago
- AI-based research for supplementation protocols☆23Mar 16, 2025Updated last year
- Official CoinMarketCap CLI for market data, history, monitoring, and AI-agent workflows.☆16Apr 9, 2026Updated 4 months ago
- ☆38Mar 22, 2026Updated 4 months ago
- Aleksei Dolgikh GitHub Profile Readme 🎴🦄🚀 #alexdolbun #unicornwitnesses☆12May 27, 2025Updated last year
- BAI tools☆20Apr 18, 2026Updated 3 months ago
- Just example how you can write app with Flutter☆17Sep 6, 2020Updated 5 years ago
- Create your own CUSTOMIZED Dolphin Mixtral 8x7b & Dolphin Llama 3 model using Ollama☆15Apr 24, 2024Updated 2 years ago
- ☆18Mar 26, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Universal Ethernet Direct Connect (UniEDC)☆32Apr 1, 2026Updated 4 months ago
- static embedding models in golang☆20Mar 13, 2026Updated 4 months ago
- SDK to build on staking program that allows top stakers to earn fee from dynamic-amm locked escrow☆12May 19, 2025Updated last year
- ☆14May 20, 2022Updated 4 years ago
- ☆15Feb 26, 2026Updated 5 months ago
- Local LLM chat panel for ComfyUI — LM Studio & Ollama, multi-session, vision support, Guide Materials☆24Jun 21, 2026Updated last month
- Example of using the sikuli gem to test user interface interaction☆17Dec 4, 2011Updated 14 years ago
- 🔵 How I backup, restore and synchronise my shell / system preferences and settings.☆13Jul 28, 2026Updated last week
- GitHub Aleksei Dolgikh https://alexdolbun.com HUB information for search engines like Google.com, Yandex.ru, Yahoo.com, Bing.com and etc.…☆10Nov 2, 2024Updated last year
- 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.
- ☆22Jun 6, 2026Updated 2 months ago
- The brutalist UI components package, built for extendability and compatibility☆11Jun 23, 2026Updated last month
- TurboQuant KV Cache Compression for llama.cpp — 5.2x memory reduction with near-lossless quality | Implementation of Google DeepMind's …☆90Updated this week
- MCP Proxmox Server☆20Nov 1, 2025Updated 9 months ago
- Let any AI agent run DaVinci Resolve — MCP server with live Studio control, free-edition FCPXML/LUT workflows, reference color matching, …☆29Jul 20, 2026Updated 2 weeks ago
- JVMTI agent which calls mlockall and setuids down to a target user upon initialization☆21Sep 13, 2011Updated 14 years ago
- A quick tutorial on creating web applications in Python with Taipy☆10Nov 30, 2024Updated last year