This repo is a alternative solution for standard self-attention. It uses tree routing with learnable functions for cheaper self-attention while not compromising accuracy.
☆39Oct 11, 2026Updated last week
Alternatives and similar repositories for Adaptive-Learnable-Hierarchical-Routing-
Users that are interested in Adaptive-Learnable-Hierarchical-Routing- are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Zero downtime embedding upgrades☆54Sep 15, 2026Updated last month
- ☆20Updated this week
- Spend fewer tokens on the same work. A local CLI that finds wasted tokens in Claude Code, Codex and your own API calls.☆87Updated this week
- The official Terraform provider for OpenAI.☆36Updated this week
- Offline disassembler for ARM64, ARM32, x86-64, x86 (32-bit), WebAssembly, .NET (CIL), and Java bytecode. Supports Mach-O, ELF, PE, APK, a…☆45Updated 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.
- 249M-param MoE transformer built from scratch in PyTorch. GQA, RoPE, SwiGLU, sparse MoE with 3 aux losses, AMP training loop no Trainer a…☆19May 22, 2026Updated 4 months ago
- Ornith-1.5-35B-A3B (NVFP4 + FP8 + MTP) on NVIDIA DGX Spark (GB10)☆29Oct 6, 2026Updated last week
- Drop-in causal memory for AI agents. Append-only event store with associations and bounded memory injection.☆25Aug 6, 2026Updated 2 months ago
- [H] HyperspaceDB is a high-performance, vector database. It features 1-bit quantization, async replication, and native support for hierar…☆162Updated this week
- Composable Python reinforcement-learning library for Trackmania 2020: training, evaluation, custom models and game integration.☆27Updated this week
- Implementation of the recurrent looped transformer proposed by Yifan Zhang of Princeton☆61Sep 26, 2026Updated 3 weeks ago
- Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any …☆90Oct 7, 2026Updated last week
- Continual Learning Mechanisms Compose for Long-Horizon Memorization☆24Sep 16, 2026Updated last month
- Is a high-performance Augmented Recovery-Generation (RAG) solution based on Redis, Qdrant or PostgreSQL. It offers a high-level interface…☆30Jan 6, 2026Updated 9 months ago
- 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.
- A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.☆136Sep 19, 2026Updated 3 weeks ago
- Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell☆71Updated this week
- ☆31Jul 24, 2026Updated 2 months ago
- Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. St…☆58Jun 17, 2026Updated 4 months ago
- Verified code context for agents☆66Updated this week
- An 18 notebook course that isolates and measures each component of agentic loop engineering on real, industry standard software datasets.☆59Jun 29, 2026Updated 3 months ago
- JAX Multi-Agent RL, Neuro-Evolution, and A-Life Library☆15Oct 12, 2025Updated last year
- A lightweight CLI tool for RAG over local documents☆32Sep 11, 2026Updated last month
- Convert long AI conversations into portable conversation state graphs for LLM handoffs.☆35May 30, 2026Updated 4 months ago
- 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.
- ☆33Jun 18, 2025Updated last year
- CDRAG is a new retrieval framework that uses hierarchical document clustering, and LLM-guided document selection from those clusters to c…☆39Apr 13, 2026Updated 6 months ago
- Salt encrypts your agent's files and database memories before they leave your machine.☆27Oct 11, 2026Updated last week
- Rasterize and Ray Tracing with ANE☆37Updated this week
- Demo of fine-tuning QA models for answering FAQ of cloud providers documentation☆11Jun 20, 2026Updated 3 months ago
- Mixed-vendor GPU inference cluster manager with speculative decoding☆38Jul 2, 2026Updated 3 months ago
- On device Firewall for Coding and Personal Agents☆1,605Sep 5, 2026Updated last month
- Native Hermes Desktop dock for direct profile chat, concurrent jobs, cancellation, and explicit Kanban assignment.☆44Aug 23, 2026Updated last month
- An open source project of a low-cost quadruped robot developed with Jetson Nano.☆22Jul 22, 2023Updated 3 years ago
- 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.
- Basic Space Invaders clone written in Love2D☆12Jan 21, 2015Updated 11 years ago
- ☆19Jul 25, 2022Updated 4 years ago
- JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.☆75Sep 18, 2026Updated last month
- A Cities: Skylines-class city builder running in the browser, built in Three.js by AI agents. Code ships when it's finished.☆81Sep 2, 2026Updated last month
- Playdate implementation of the Voxel Space Algorithm☆13May 11, 2023Updated 3 years ago
- GLM-5.3-Flash (NVFP4) at TP=4 across 4x ASUS GX10 / GB10 - vLLM + mentat instead of Ray, 524k context, DFlash2. Minimal working recipe.☆89Updated this week
- Minimal read-only OS image for GB10 (DGX Spark / ASUS GX10) boxes☆89Oct 4, 2026Updated 2 weeks ago