Skip to content
#

cache-compression

Star

Here are 3 public repositories matching this topic...

Language: All
Filter by language
All 3 Jupyter Notebook 1 Python 1 Verilog 1
ChaosEngineAI

cryptopoly / ChaosEngineAI

Sponsor
Star 17

Local AI workstation — discover, run, chat, benchmark, and generate images from open-weight models. DFlash/DDTree speculative decoding, five cache compression strategies (RotorQuant, TriAttention, TurboQuant, ChaosEngine), MLX + llama.cpp + vLLM backends.

desktop-app python machine-learning typescript ai image-generation mlx tauri huggingface apple-silicon openai-api cache-compression llm stable-diffusion llama-cpp vllm local-ai gguf speculative-decoding dflash
  • Updated Apr 25, 2026
  • Python

suhasramanand / kv-cache-compression

Star 0

Research-quality implementation of KV cache compression strategies for efficient long-context LLM inference. Comprehensive evaluation of H2O, semantic clustering, and learned eviction policies achieving 50-87.5% compression with minimal quality degradation.

research pytorch attention-mechanisms transformer-architecture memory-optimization kv-cache cache-compression long-context llm-inference h2o-cache
  • Updated Dec 26, 2025
  • Jupyter Notebook

Improve this page

Add a description, image, and links to the cache-compression topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the cache-compression topic, visit your repo's landing page and select "manage topics."

Learn more