a LLM inference engine to run on consumer hardware
☆47Apr 15, 2026Updated 4 months ago
Alternatives and similar repositories for tachyon
Users that are interested in tachyon are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- a personal collection of my notes for ml sys☆120Aug 8, 2026Updated 2 weeks ago
- a minimal paged attention implementation☆20Jan 30, 2026Updated 6 months ago
- a simple c++ inference engine for gpt based architecture☆40Dec 10, 2025Updated 8 months ago
- ☆18Jun 26, 2024Updated 2 years ago
- NCCL communication API layer, and transport layer created from first principles.☆16Aug 20, 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.
- Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).☆21Jul 11, 2026Updated last month
- An expense tracking application that embodiesminimalist design philosophy with clean typography, subtle shadows, and elegant micro-intera…☆15Aug 31, 2025Updated 11 months ago
- [MLSys 26] 🥇 Solution for Gated Delta Net Track of MLSys 26 Flash infer competition☆36May 22, 2026Updated 3 months ago
- fastcv is a CUDA rewrite of the opencv filters with python bindings☆73Oct 10, 2025Updated 10 months ago
- RISC-V 64 hypervisor written in Rust☆23May 29, 2026Updated 2 months ago
- Multithreaded chat app server built on top of my own websocket echo server from scratch. Load-tested for 1,000 clients with highest throu…☆17Dec 16, 2025Updated 8 months ago
- ☆25Apr 4, 2026Updated 4 months ago
- a programming language written from scratch in python☆15Oct 22, 2025Updated 10 months ago
- ☆12Jun 14, 2024Updated 2 years 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.
- An Emacs-inspired C++20 terminal editor. No Lisp. No bloat.☆21Updated this week
- A Python DSL for Apple Metal GPU compute☆25Jul 23, 2026Updated last month
- Code for MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization☆23Feb 18, 2026Updated 6 months ago
- ☆20Apr 26, 2026Updated 3 months ago
- Repository for the CUDA H100 Course☆73Apr 12, 2026Updated 4 months ago
- GPU kernel benchmarking☆47Jun 10, 2026Updated 2 months ago
- ☆51Updated this week
- AI Research Agent is a versatile application that leverages multiple tools to conduct thorough research on any topic.☆12Oct 12, 2024Updated last year
- Cuda implemenation of flash-kmeans, 2x faster☆23May 8, 2026Updated 3 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.
- A high-performance job scheduler designed for microsecond latency (<5us P50 latency) and massive concurrency (highest throughput : 2M+ jo…☆30Jan 11, 2026Updated 7 months ago
- a tiny regex engine written in go☆24Oct 13, 2023Updated 2 years ago
- Typescript UI library ^^☆35Oct 29, 2025Updated 9 months ago
- High-performance GPU kernels for LLM inference in OpenAI Triton. Fused RMSNorm, SwiGLU, INT8 GEMM with benchmarks and roofline analysis.☆40Jul 22, 2026Updated last month
- Performant, beautiful, and easy-to-write GUIs for everyone, everywhere.☆39Aug 13, 2026Updated last week
- virtual machine in C☆31Apr 19, 2026Updated 4 months ago
- ☆14Dec 31, 2024Updated last year
- a bot that fetches attendance☆12May 16, 2025Updated last year
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆61Apr 18, 2026Updated 4 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Official codebase for the MLSys 2026 paper "IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference". It enables hi…☆21May 29, 2026Updated 2 months ago
- Examples in the MLX framework☆11Sep 23, 2024Updated last year
- ☆98Aug 16, 2026Updated last week
- Build Agentic workflows with function calling using open LLMs☆27Aug 3, 2026Updated 2 weeks ago
- Educational WIP☆73Feb 16, 2026Updated 6 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆268Updated this week
- ☆21May 28, 2024Updated 2 years ago