My reasearch of losslessly compressing LLM weights.
☆66Jul 23, 2026Updated 3 months ago
Alternatives and similar repositories for weight-compression
Users that are interested in weight-compression are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Dynamic per-token early exit for LLM inference. Skip layers tokens don't need☆34Sep 18, 2026Updated last month
- turn qwen 3.6 27B-> AR -> diffusion (opendllm + d3llm)☆15Jun 11, 2026Updated 5 months ago
- local distributed learning and inference☆14May 27, 2026Updated 5 months ago
- vLLM inference solutions for NVIDIA GB10 (DGX Spark, sm121) — KIMI-K3 B12X_MLA + DSpark, GLM-5.2☆69Sep 30, 2026Updated last month
- ☆15Jan 14, 2026Updated 9 months ago
- 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.
- Submodule of evalverse forked from [google-research/instruction_following_eval](https://github.com/google-research/google-research/tree/m…☆15May 4, 2024Updated 2 years ago
- Record your own speech with a big model listening, then fine-tune a small fast one on it: a recipe for you and your coding agent.☆20Oct 18, 2026Updated 3 weeks ago
- Evalution: evolve your LLMs with better evals.☆17Updated this week
- cleans build files☆18Jul 29, 2026Updated 3 months ago
- Flow Map Speculative Decoding☆58Nov 3, 2026Updated last week
- Small System One decision models (17M–400M) for Yes/No, Choice, Score, and reranking. Training toolkit, Python inference, and ONNX suppor…☆42Oct 15, 2026Updated 3 weeks ago
- Double-click installer for MiniMax-H3 Turbo video, auto-maps to your RTX or GTX or DGX Spark , such as 3090, 4090 etc.☆20Aug 25, 2026Updated 2 months ago
- (Continuously) scans your internet facing infrastructure to discover exposed ports and services, helping you identify changes and reduce …☆12Updated this week
- Demo of knowledge graph creation and Graph RAG with Dspy and Kuzu☆22Jun 30, 2025Updated last year
- 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.
- Open quantization tooling for TurboQuant-style low-bit LLM releases, stock GGUF deployment, and Apple Silicon runtime experiments.☆10May 5, 2026Updated 6 months ago
- GLM-5.2 on 4x DGX Spark with adaptive MTP K2/K4/K5, FULL CUDA graphs, DCP2, 520K context, and a downloadable ARM64 runtime image.☆13Aug 8, 2026Updated 3 months ago
- Allows Codex on macOS to patch and extend its own desktop app.☆18Mar 24, 2026Updated 7 months ago
- Autonomous self-improving 4x DGX Spark (GB10) MoA stack + LoRA loop (DSV4F router, Qwen3.6/Omni/TwoTower/Gemma). Hermes MoA routing, ~90%…☆24Aug 17, 2026Updated 2 months ago
- A Dolphin-like file manager for kitty, built with ratatui.☆13Updated this week
- ☆11Jul 10, 2026Updated 4 months ago
- Pure-Rust port of CerebroCortex — brain-analogous AI memory system with ACT-R/FSRS activation, associative networks, 8-phase dream engine…☆16Aug 9, 2026Updated 3 months ago
- An OpenCode plugin that lets AI agents control Windows desktops directly using the \windows-mcp\ MCP server.☆19Jul 10, 2026Updated 4 months ago
- ☆49Jan 3, 2026Updated 10 months ago
- 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.
- GLM-5.2 QuantTrio TP=4+DCP2 on 4x NVIDIA DGX Spark (GB10) — tuned and measured under a real agent workload. Adaptive MTP, the indexer law…☆20Aug 24, 2026Updated 2 months ago
- Out-of-tree Linux thunderbolt_net driver (DKMS) tracking upstream, with a receive-side workaround for macOS Thunderbolt Bridge TCP aggreg…☆18Oct 18, 2026Updated 3 weeks ago
- Lightweight ternary QAT for ternary Bonsai models by Prism-ML☆16Sep 18, 2026Updated last month
- RAG parameter sweep and evaluation toolkit — a practical way to test how different vector databases, embedding models, chunking strategie…☆21Updated this week
- ☆35Mar 9, 2025Updated last year
- ☆14Aug 21, 2026Updated 2 months ago
- ComfyUI node that removes the invisible diffusion noise residue☆16Apr 14, 2026Updated 6 months ago
- SGLang kernel library for Intel XPU☆37Updated this week
- Compute Where It Counts: Scaling both speed and quality with training compute☆13Sep 18, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Compute on a real brain - the complete fruit-fly connectome run as a reservoir. Reads handwriting at 94%. Wiring is fixed biology; only t…☆20Sep 12, 2026Updated 2 months ago
- The official Python SDK for the Perceptron API☆70Oct 14, 2026Updated 3 weeks ago
- Gemini evaluations☆29Sep 3, 2026Updated 2 months ago
- Serve LibertAIDAI/GLM-5.3-Flash-NVFP4 on 2x NVIDIA DGX Spark (GB10) with patched vLLM TP=2, 262k context, MTP-4.☆21Nov 2, 2026Updated last week
- Swift markdown parsing and rendering library for iOS/macOS. Streaming, theming, LaTeX, syntax highlighting.☆26May 18, 2026Updated 5 months ago
- PyTorch implementation of "SelectiveNet: A Deep Neural Network with an Integrated Reject Option" from Geifman et al. [ICML2019]☆10Oct 6, 2022Updated 4 years ago
- A naive attempt at generating better prompts for opencode using DSPy☆19Nov 29, 2025Updated 11 months ago
Are these results useful?