Model-agnostic MoE compression automation: build calibration bundles, run REAP/quantization/benchmark/publish stages, and render auditable reports.
☆183Mar 22, 2026Updated 7 months ago
Alternatives and similar repositories for moe-compress
Users that are interested in moe-compress are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- LLM inference in C/C++☆19Nov 8, 2026Updated 2 weeks ago
- A pixel art space shooter built entirely by a 9B AI model on a single RTX 3060. Zero hand-written code.☆106Mar 19, 2026Updated 8 months ago
- Run a fleet of coding agents, each alone in its own VM on boat.dev, from your Mac or Linux desktop.☆22Updated this week
- extract all your personal data history from cursor, codex, claude-code, windsurf, and trae☆1,355Oct 7, 2026Updated last month
- ☆25Nov 13, 2026Updated last week
- 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.
- Fast Opportunistic Mixture-Of-Experts. From-scratch C/HIP MoE inference with multi-tier caching and cache-aware routing. First ever examp…☆32Mar 31, 2026Updated 7 months ago
- 1bit llama.cpp gguf weights paired with turboquant 4 bit kv cache☆23Apr 4, 2026Updated 7 months ago
- Control panel for VLLM, Sglang, llama.cpp, exllamav3☆1,854Oct 26, 2026Updated 3 weeks ago
- Your own eval engineer☆14May 10, 2026Updated 6 months ago
- ProxySoul × Empryo: skills, agents, an immune system and habits for coding agents. soulstack.proxysoul.com☆30Oct 22, 2026Updated 3 weeks ago
- ☆14Jun 12, 2026Updated 5 months ago
- Local-first Routing for using Switchyard in Hermes☆47Updated this week
- SHA-256 in Bend with a machine-checked functional correctness proof against a separate FIPS 180-4 specification.☆20Sep 20, 2026Updated 2 months ago
- Moshi-Finetune-MLX lets you fine-tune Moshi (Native, Real-Time, Speech-to-Speech) models all on Apple Silicon.☆26Apr 21, 2026Updated 7 months ago
- 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.
- Machine Learning in Bend 2: Dependent Types, Shapes at the Type Level, and Proven Laws☆22Nov 11, 2026Updated last week
- Reason over explicit states, many branches at once: merge duplicates, cancel dead ends, advance together.☆181Oct 3, 2026Updated last month
- Ship your repo + live coding-agent session (Claude Code / Codex / pi / Droid) to another machine over Tailscale; it resumes in tmux and k…☆175Sep 3, 2026Updated 2 months ago
- Webcam to hand gesture and facial expression with Liquid AI's d1-2B on Apple Silicon (mlx-vlm), zero tokens generated☆51Updated this week
- Doomscroll your way to knowledge. An infinite-scroll feed of core engineering concepts, styled like X/Twitter.☆25Apr 20, 2026Updated 7 months ago
- A skill and CLI that lets small local models like LFM3-1.7B make 3D printable parts, from words or a picture, even through context compac…☆81Updated this week
- Switch your entire Omarchy desktop into the way you work: workspaces, notifications, audio, wallpaper, theme, apps, and commands, per mod…☆14Sep 9, 2026Updated 2 months ago
- Locate an audio or video recording from the Doppler curves of propeller aircraft, matched against archived ADS-B flight tracks. Rust, on …☆42Updated this week
- LocalAGI agent hub☆17Mar 16, 2026Updated 8 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.
- Your AI friend right in your browser☆549Oct 30, 2026Updated 3 weeks ago
- The best benchmark for LLMs on Apple's MLX framework knowledge and coding tasks.☆38Jun 12, 2026Updated 5 months ago
- Lua 5.5 in Zig, with no C.☆18Nov 9, 2026Updated last week
- Codebase for the paper "Biases in the Blind Spot: Detecting What LLMs Fail to Mention"☆21May 28, 2026Updated 5 months ago
- Point any coding harness (Claude Code, Codex, OpenCode, Pi, OMP, Crush, Copilot, Grok…) at any OpenAI/Anthropic/Responses-compatible infe…☆92Sep 27, 2026Updated last month
- Applying the Chinese Wall Reverse Engineering Technique to Large Language Model Code Editing☆12Aug 2, 2025Updated last year
- Autoresearch-style AI agent loop for trading strategy optimization (SPY + VIX backtest)☆12Mar 12, 2026Updated 8 months ago
- Fastest validated sglang recipe for Qwen3.8-27B (AWQ-INT4 + DSpark) on RTX 3090s — 1×/2×/4× GPU presets, image+video, full benchmarks☆66Oct 17, 2026Updated last month
- Speeds up TTFT☆24Sep 25, 2026Updated last month
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆14Updated this week
- experiment loop for ai agents and swarms☆173Mar 29, 2026Updated 7 months ago
- ☆130Mar 7, 2026Updated 8 months ago
- Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port wi…☆146Apr 15, 2026Updated 7 months ago
- Fast Qwen3.8-27B for one RTX 3090. 200k context, 100+ tok/s. Custom CUDA decode engine, OpenAI-compatible API.☆49Updated this week
- A hive mind communication platform☆23Aug 2, 2026Updated 3 months ago
- Local AI registry: one validated recipe per machine, with the evidence attached☆387Updated this week
Are these results useful?