Proof of concept: Exploiting temporal coherence in LLM inference-- delta encoding for KV cache compression and weight-skip prediction. Achieves F16-quality KV cache at Q4_0 compression ratios with zero perplexity loss on llama.cpp.
☆50Apr 10, 2026Updated 5 months ago
Alternatives and similar repositories for delta-compress-llm
Users that are interested in delta-compress-llm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Editor Code Assistant (ECA) integration for Vscode☆17Sep 15, 2026Updated last week
- A sleek, customizable interface for managing LLMs with responsive design and easy agent personalization.☆19Aug 30, 2024Updated 2 years ago
- Specialized AI agents for your bare metal. 100% On-Prem & Air-Gap ready.☆26Feb 21, 2026Updated 7 months ago
- Specialized fork for (relatively) fast single-GPU inference (in CUDA) using large MoE models that don't fit fully into VRAM☆17May 6, 2026Updated 4 months ago
- Tensor parallelism is all you need. Run LLMs on an AI cluster at home using any device. Distribute the workload, divide RAM usage, and in…☆18Nov 11, 2024Updated last year
- 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.
- Inference Llama 2 with a model compiled to native code by TorchInductor☆14Feb 8, 2024Updated 2 years ago
- Debian packaging for NNCP [archived], moved to https://salsa.debian.org/go-team/packages/nncp☆14Feb 18, 2023Updated 3 years ago
- ☆18Jul 1, 2025Updated last year
- Handle Android "draw over other apps" permissions and queries in a version-agnostic way☆22Jun 17, 2019Updated 7 years ago
- Random AI notes for working with local models or playing around with random machine learning bits.☆64Jun 7, 2026Updated 3 months ago
- Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms…☆50Aug 9, 2026Updated last month
- AI plays Doom — pit Vision Language Models against demons and each other. Solo scenarios, deathmatch arena, 1-4 agents with any OpenAI-co…☆20Mar 12, 2026Updated 6 months ago
- ☆20Sep 28, 2024Updated 2 years ago
- A high performance authentication and access-control gateway for LLM API backends☆16Jun 11, 2026Updated 3 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.
- ☆27Updated this week
- High-efficiency LLM inference engine in C++/CUDA. Run Llama 70B on RTX 3090.☆466Feb 22, 2026Updated 7 months ago
- pix2pix model for generating terrain☆17Jan 7, 2023Updated 3 years ago
- ☆11Oct 25, 2021Updated 4 years ago
- ☆24Jan 22, 2025Updated last year
- ☆23Aug 9, 2024Updated 2 years ago
- Using embeddings compressed by Product Quantization, in Javascript☆31Jul 6, 2023Updated 3 years ago
- Rust port of the streaming ddelta patch algorithm, based on bsdiff☆12May 2, 2024Updated 2 years ago
- LLM inference in C/C++☆23Oct 4, 2024Updated 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.
- A crates.io custom registry API receiver impl & Git backend controller.☆12Nov 13, 2020Updated 5 years ago
- Synchronises Ableton Live to a live input such as microphone in the room or DJ playing record☆11Aug 14, 2014Updated 12 years ago
- VellumForge2 is a Golang CLI for generating high-quality Direct Preference Optimization datasets via a hierarchical prompt pipeline with …☆22Feb 15, 2026Updated 7 months ago
- A collection of very basic allocators. Written with WebAssembly in mind.☆15Jan 12, 2024Updated 2 years ago
- Official code of "ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction", IJCAI2025☆32Mar 10, 2026Updated 6 months ago
- Additional 3rd party software used in Playbit. See playbit/public for most 3rd party software☆13Jul 14, 2025Updated last year
- Count Min Sketch implementation for Rust☆15Updated this week
- the most complete serialization tree for serde☆16Apr 24, 2024Updated 2 years ago
- Nothing to see here yet ...☆13Jun 28, 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.
- ☆18Mar 12, 2026Updated 6 months ago
- ☆12Dec 3, 2025Updated 9 months ago
- Classifies percussion audio samples with a CNN-LSTM, written in python and pytorch. Also exports to Drumkv1 (lv2 plugin)☆14Aug 20, 2020Updated 6 years ago
- Yet another frontend for LLM, written using .NET and WinUI 3☆11Sep 14, 2025Updated last year
- ☆27Sep 25, 2024Updated 2 years ago
- Screw You Guys I'm Going Home☆10Jan 28, 2023Updated 3 years ago
- Scale OpenClaw from one AI assistant to a coordinated fleet — shared knowledge, collective memory, distributed goals.☆30Apr 13, 2026Updated 5 months ago