SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places attention and hot experts where they fit.
☆199Aug 7, 2026Updated this week
Alternatives and similar repositories for pulsar
Users that are interested in pulsar are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Frequency-based KV cache pruning for llama.cpp — 25% cache reduction, improved PPL at long context. GPU compaction kernel for HIP/ROCm.☆16Apr 18, 2026Updated 3 months ago
- Open-source options gamma exposure (GEX) & positioning dashboard — dealer GEX, max pain, open interest, IV surface. Self-hosted, Docker, …☆45Updated this week
- ☆25Jul 13, 2026Updated 3 weeks ago
- Geometric agent memory for Agents: 8-tool lean contract, harness injection at wake, session handoff. 79 MCP tools. Not a vector DB. Rust …☆17Updated this week
- A cognition kernel that wraps a frozen LLM in a persistent identity + trust + governance loop — testing whether capability comes from str…☆23Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A ComfyUI custom node enabling **Flash Attention 1** on legacy NVIDIA GPUs (Tesla V100, T4) that lack Compute Capability 8.0+ required by…☆18Feb 9, 2026Updated 6 months ago
- Extract a single expert from a Mixture Of Experts model using slerp interpolation.☆19May 26, 2024Updated 2 years ago
- OpenAI's Code Interpreter running locally, as a service via WebSocket☆10Sep 22, 2023Updated 2 years ago
- The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, mem…☆18Updated this week
- ComfyUI-KokoroTTS: A text-to-speech model that utilizes the Kokoro TTS framework to convert text into natural-sounding speech. It suppor…☆13Apr 18, 2025Updated last year
- Self-hosted, Flutter-first mobile CI and internal app distribution platform.☆26Updated this week
- Public repo for kernel writing skills in CuTeDSL, Triton, Tilelang and CUDA☆24Jul 7, 2026Updated last month
- 🛡️ Programmable Guardrails for LLM Applications in Java. A framework-agnostic toolkit for input/output validation, PII masking, and jail…☆16Apr 15, 2026Updated 3 months ago
- BASIC reborn for the AI era: APL-style arrays, SDL3 games, native LLVM compile, Win32 forms, local LLMs, and a built-in MCP server your A…☆15Updated this week
- 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.
- AI-powered personal knowledge vault☆14Aug 1, 2026Updated last week
- Vectorless code retrieval for AI coding agents — search code by business intent (@intent, @domainRule) over a Tree-sitter graph. Built f…☆17Updated this week
- Your daily AI intelligence dispatch to Email 📧· Robotics, Agents & LLMs analyzed by Claude Opus · 每日多源聚合 + 深度分析，GitHub Actions 一键部署，无需服务…☆22Updated this week
- A native, performance-first ADE built with Flutter, Rust, and Ghostty. Run Claude Code, Codex, Amp, and other CLI coding agents in parall…☆16Updated this week
- Unicode-aware string utilities for Go☆22Sep 1, 2022Updated 3 years ago
- AI Access Proxy Layer — granular permission gateway for AI agents. Connect services, define scopes, get an MCP endpoint.☆15Updated this week
- 开源、本地优先的 AI 长篇小说创作引擎：多智能体世界推演、按弧规划、RAG 长程记忆、逐章审核与断点恢复 | Open-source AI novel generator for long-form fiction.☆72Jul 25, 2026Updated 2 weeks ago
- A proxy that hosts multiple single-model runners such as LLama.cpp and vLLM☆12May 30, 2025Updated last year
- Generate a diverse dataset of 100 face-swapped images using the Inswapper model for training robust face-swap detection classifiers. 🖼️�…☆20Updated this week
- 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.
- AI Research Dashboard — Latest AI/ML papers, models, repos, trends & news, auto-updated every hour☆13Updated this week
- NuxtJS module for Nhost☆10Jan 26, 2022Updated 4 years ago
- Scalable, high-performance C++23 framework for evolutionary algorithms, including genetic programming, genetic algorithms, and differenti…☆19Updated this week
- TypeScript framework for building AI agents — multi-provider (Anthropic, OpenAI, Google), tool calling, permissions, hooks, streaming, an…☆19Updated this week
- Multi-Workspace IDE for Parallel AI Agent Development☆20Updated this week
- Dotfiles which bring the Omarchy experience to MacOS (THIS IS NOW A MIRROR OF https://codeberg.org/matt-dong-123/dotfiles)☆18Jul 30, 2026Updated last week
- ☆15Jan 8, 2025Updated last year
- PyTorch research stack for ML multi-factor trading: 213 factors, bias correction, portfolio optimization, and vectorized backtesting.☆69Updated this week
- Interactive chord identification and harmony exploration, with live MIDI and manual input☆22Updated this week
- 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.
- TQ3 KV cache compression for ComfyUI. 4.6x VRAM savings for video generation. Enables LTX-2.3 22B on V100 32GB.☆38Updated this week
- My reasearch of losslessly compressing LLM weights.☆64Jul 23, 2026Updated 2 weeks ago
- How much experts do we need to serve a model?☆152Mar 18, 2026Updated 4 months ago
- A save editor for Monster Hunter XX for the Nintendo 3DS.☆10May 7, 2019Updated 7 years ago
- A better way to handle errors. Both data and errors are declared with const, available at the top level, and non-nullable (once the other…☆11Sep 5, 2024Updated last year
- The loop never sleeps — you finally can. Agents automate the entire development lifecycle (write, review, merge, learn) end to end, with …☆21Updated this week
- AI POCS: ML, NLP, LLM, Vision, Classification, clustering, GenAI, Transformers, PyTorch, Keras, All things AI POCS.☆21Updated this week