This repo implements a generic version of the REAM algorithm described in “REAM: Compressing Mixture-of-Experts LLMs” and makes it easy to apply to different MoE model families such as Qwen, gpt-oss, Kimi Linear, etc.
☆11Aug 29, 2026Updated 2 months ago
Alternatives and similar repositories for ream
Users that are interested in ream are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MoE expert compression toolkit — prune, merge, and forge specialist models for local inference.☆14Nov 3, 2026Updated last week
- CLaude Code 个性化规则【含 前端、后端（Python）、以及其他个人习惯】☆14Jan 11, 2026Updated 10 months ago
- Rust implementation + Python bindings for image effects used in chaiNNer☆13Jun 11, 2024Updated 2 years ago
- [WIP]Custom nodes for handling, inspecting, modifying and creating various model files.☆17Updated this week
- 中医书籍文献等材料的高质量文本数据☆24Apr 22, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆29Oct 19, 2025Updated last year
- ☆17Sep 25, 2026Updated last month
- A Chrome browser extension that seamlessly integrates MCP (Model Context Protocol) tools directly into Perplexity's web interface, and co…☆15Jul 7, 2026Updated 4 months ago
- ☆19Aug 7, 2026Updated 3 months ago
- PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose Estimation☆13Sep 18, 2025Updated last year
- code of sasmamba☆12Dec 20, 2025Updated 10 months ago
- 基于大模型搭建的微信聊天机器人，同时支持微信、企业微信、公众号、飞书接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。☆14Jan 15, 2024Updated 2 years ago
- ☆20Jul 23, 2026Updated 3 months ago
- Official PyTorch implementation of the paper "KASportsFormer: Kinematic Anatomy Enhanced Transformer for 3D Human Pose Estimation on Shor…☆13Jul 29, 2025Updated last year
- 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.
- Local AI model manager☆16May 21, 2026Updated 5 months ago
- ☆12Nov 14, 2025Updated 11 months ago
- Merge models by preset☆35Mar 27, 2025Updated last year
- Python library for Telize JSON IP and GeoIP REST API☆12Nov 26, 2015Updated 10 years ago
- Qwen3/3.x engine with SSD offload☆11Oct 14, 2026Updated 3 weeks ago
- ForgeAI : Your local model workshop, Load. Inspect. Merge. Ship.☆16Feb 10, 2026Updated 9 months ago
- [NeurIPS 2026] Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning☆26Oct 19, 2026Updated 3 weeks ago
- Stabilizing PPO in LLM post-training via robust critic learning https://arxiv.org/pdf/2609.36802☆25Updated this week
- ☆17Jun 18, 2026Updated 4 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Hermes Desktop for Windows☆11May 30, 2026Updated 5 months ago
- ☆12Mar 17, 2015Updated 11 years ago
- MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation☆17Nov 15, 2025Updated 11 months ago
- Unified terminal monitor for AMD Ryzen AI NPU (XDNA) + iGPU — live utilization for Strix Halo, where amd-smi comes up empty☆40Oct 18, 2026Updated 3 weeks ago
- MX Systolic Arrays on FPGAs☆14Oct 26, 2026Updated 2 weeks ago
- Huggingface but for inference engines.☆14Updated this week
- Downhill Mayhem — a free fan-made browser tribute to Downhill Domination (PS2, 2003).☆13Nov 2, 2026Updated last week
- Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on loca…☆21Updated this week
- A Python base cli tool for caption images with WD series, Joy-caption-pre-alpha,meta Llama 3.2 Vision Instruct and Qwen2 VL Instruct mode…☆45Oct 30, 2025Updated last year
- 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.
- ☆17Oct 2, 2026Updated last month
- Django Productivity Tools☆13May 13, 2011Updated 15 years ago
- ☆16Jun 15, 2025Updated last year
- Qwen 3.8 Next Flash toolbox utilizing pwilkin's strix-halo llama.cpp fork☆13Sep 16, 2026Updated last month
- User Script for http://workflowy.com that adds some extra features.☆12Oct 22, 2017Updated 9 years ago
- Generalized app for two-step verification.☆12Feb 28, 2024Updated 2 years ago
- A lightweight operating system abstraction layer for agents.☆20Dec 26, 2025Updated 10 months ago
Are these results useful?