lithos-metal: high-performance LLM inference kernels and serving for Apple silicon.
☆335Oct 21, 2026Updated 2 weeks ago
Alternatives and similar repositories for lithos-metal
Users that are interested in lithos-metal 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 local inference engine for Apple silicon, built around the model.☆2,110Updated this week
- Autonomous CUDA kernel optimization agent with structured task specs and per-config scoring☆19Jun 17, 2026Updated 4 months ago
- Sushi engine runs very high quality quant model in Apple Silicon, using both STQ and EXL3 format with special tuning technology.☆421Updated this week
- Native SwiftUI trading charts for iOS: candles, indicators, crosshair, drawing tools and paged history, on Swift Charts.☆14Oct 7, 2026Updated 3 weeks ago
- LLM Inference Engine for Metal, CUDA and Vulkan.☆1,677Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- An Open Compiler Harness for Agentic GPU Programming☆194Updated this week
- An Attention Superoptimizer☆22Jan 20, 2025Updated last year
- ☆62Updated this week
- Research MIL-to-HWX compiler for the M4 Apple Neural Engine☆17Sep 3, 2026Updated 2 months ago
- Idol: a single image to 3D Gaussians. Inference SDK and demo.☆19Updated this week
- Our lightning-fast inference engine.☆276Oct 27, 2026Updated last week
- Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with c…☆2,389Updated this week
- A high-performance inference engine for AI models☆3,230Updated this week
- The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B…☆2,673Updated this week
- 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.
- Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Acc…☆543Oct 28, 2026Updated last week
- Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully nati…☆652Updated this week
- ☆213Sep 10, 2026Updated last month
- See where local inference loses speed on Apple Silicon under Linux☆14Updated this week
- PTXBench: an open-source environment to evaluate GPU kernel languages for LLM agents☆38Updated this week
- A Long-Horizon Benchmark for Self-Improving Inference Systems☆140Oct 26, 2026Updated last week
- MLTF: Qwen3.8-27B q8c inference for Apple Silicon☆14Oct 8, 2026Updated 3 weeks 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
- DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers☆533Sep 30, 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.
- 🧱 Experimental library for building inference engines☆410Updated this week
- An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.☆222Aug 30, 2026Updated 2 months ago
- Privacy-first AI coding activity for your GitHub profile.☆19Updated this week
- Dist-MoE implements Speed-of-Light distributed Mixture-of-Experts forward and backward kernels. They are highly optimized and fused comm-…☆69Oct 29, 2026Updated last week
- Deep memory for agents over large datasets. Leviathan is a single static binary that turns your records (JSONL, JSON, CSV/TSV, SQLite, or…☆879Updated this week
- Mini-SGLang is a mini version of SGLang project ().☆13Sep 24, 2025Updated last year
- LLM serving engines that SkyDiscover builds on the fly for specific AI models and hardware: Qwen3.6-35B-A3B, Qwen3.8-Flash-Next and Flint…☆26Updated this week
- Reason over explicit states, many branches at once: merge duplicates, cancel dead ends, advance together.☆181Oct 3, 2026Updated last month
- .feels() on anything — the AI if statement as a real, typed method. Jev + BAML.☆24Sep 19, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆104Sep 8, 2026Updated last month
- Code for the paper ReplaySSM: Cache SSM Inputs, Not State☆67Oct 13, 2026Updated 3 weeks ago
- Official Inference Code of EAGLE-4☆1,157Updated this week
- LoRAFusion: Efficient LoRA Fine-Tuning for LLMs☆30Jul 2, 2026Updated 4 months ago
- Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai☆657Updated this week
- Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gem…☆735Oct 5, 2026Updated last month
- ☆29Oct 31, 2026Updated last week