A 21M-parameter LM with a 16.8M-row product-key memory: as good as a 114M dense model and runs with the table on an SSD. Triton kernels for ROCm and CUDA.
☆16Oct 23, 2026Updated this week
Alternatives and similar repositories for sparse-memory-lm
Users that are interested in sparse-memory-lm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Preference-supervised naturalness scorer for modern neural TTS . best way to measure naturalness☆21May 29, 2026Updated 4 months ago
- Real-time DPS overlay for Neverness to Everness — passive packet analysis, no memory injection. Includes party tracking, damage ECG, batt…☆42Sep 21, 2026Updated last month
- step through events! must be initialized at the top of your scripts.☆16Jul 6, 2013Updated 13 years ago
- A local prompt-difficulty classifier that automatically sets Pi reasoning effort.☆12Jul 3, 2026Updated 3 months ago
- A Node.JS based CouchDB clone optimized for SSDs☆11Jun 12, 2011Updated 15 years ago
- 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.
- Run a 177B model (Qwen3.8-Flash-Next) on an 8 GB laptop GPU. Measured: 6.6 GiB VRAM, 47.8 GiB RAM, 34-35 tok/s. The n-gram table stays on…☆24Sep 1, 2026Updated last month
- Clean reproducible benchmark suite for the self-hosted cascade RC (ARC-AGI-2, HMMT-2026, HLE, MMMU-Pro, SWE-Bench Pro, Terminal-Bench 2.1…☆13Oct 8, 2026Updated 2 weeks ago
- Intern-S2-Mobius☆59Aug 14, 2026Updated 2 months ago
- Vendor-neutral, LLM-maintained personal-context wiki. Markdown in your git, queryable by any LLM (HTTP API + MCP server). v0.7 prototype.☆20Sep 30, 2026Updated 3 weeks ago
- Fast & opinionated local AI routing: one MCP server that loads local image and video models on demand on your own GPU box (DGX Spark firs…☆10Updated this week
- This web application aims to simplify the process of creating eBay listings by leveraging data from CSV/XLS files. The app provides a use…☆14Jun 4, 2024Updated 2 years ago
- Minimal FlashAttention in CUDA C++/CuTe: readable WMMA/CuTe kernels, no NxN workspace, up to 4.5x faster than naive PyTorch☆29Jun 2, 2026Updated 4 months ago
- Analysis of the results of the paper "Predicting the direction of stock market prices using random forest" (2016) by Khaidem et al.☆13Aug 25, 2019Updated 7 years ago
- LLM quantization optimizer☆23Aug 20, 2026Updated 2 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.
- ALFI is a query language for graphical user interfaces.☆21May 31, 2020Updated 6 years ago
- A structured framework for defining, verifying and certifying AI systems.☆21Mar 11, 2025Updated last year
- Code repository for Liquid Time-stochasticity networks (LTSs)☆23Apr 26, 2023Updated 3 years ago
- ☆21Jul 23, 2026Updated 3 months ago
- https://mininavdevice.github.io/MiniNav/☆60Oct 11, 2026Updated last week
- ☆21Aug 10, 2026Updated 2 months ago
- The project aims to profile stocks with similar weekly percentage returns using K-Means Clustering. The project calculates realized volat…☆12Oct 30, 2023Updated 2 years ago
- Demo of fine-tuning QA models for answering FAQ of cloud providers documentation☆11Jun 20, 2026Updated 4 months ago
- A minimal and extensible agent server for building agent applications☆22Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Autogenerated Dart JS interop facade for the THREE WebGL javascript framework.☆29Feb 11, 2020Updated 6 years ago
- In OpenCode, models without visual capabilities are given the ability to read images, thus enabling them to have multimodal capabilities.…☆21Apr 2, 2026Updated 6 months ago
- A database-agnostic Agentic GraphRAG framework using swappable System One models (local Laya / cloud Jev). A plug-and-play intelligence l…☆51Sep 29, 2026Updated 3 weeks ago
- ☆16Jan 20, 2021Updated 5 years ago
- Inject code into .net applications☆14Nov 7, 2018Updated 7 years ago
- An MCP server for octomind tools, resources and prompts☆24Jul 1, 2026Updated 3 months ago
- Experimental validation: Agentic Search (context trees) vs traditional RAG for code retrieval. Agentic wins with 99% fewer tokens and 2× …☆13Jan 6, 2026Updated 9 months ago
- Automatically derived XHR clients for Trout routing types.☆21Jul 28, 2020Updated 6 years ago
- Lightweight OpenAI wrapper using FastAPI. Add rate limits to OpenAI usage, optionally log and store all API calls, and share regulated Op…☆15Feb 15, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Project completed during my studies at BGSE together with Travis Dunlop, Matthew Keys and Jordi Llorens☆17Sep 2, 2018Updated 8 years ago
- A small indecis model plays ViZDoom's defend_the_center☆13Oct 1, 2026Updated 3 weeks ago
- ☆20Oct 17, 2026Updated last week
- Answer-aware memory for Markdown notes: hybrid search + pluggable passage reranker, as a Claude Code plugin☆12Oct 15, 2026Updated last week
- Access your agents from any device☆19Updated this week
- Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.☆182Sep 21, 2026Updated last month
- Groq-powered MAD: The first work to explore Multi-Agent Debate with Large Language Models :D☆12Jul 5, 2024Updated 2 years ago