{"data":{"node":{"slug":"fujitsuresearch-onecompression","name":"OneCompression","tagline":"Python package for LLM compression","github_url":"https://github.com/FujitsuResearch/OneCompression","owner":"FujitsuResearch","repo":"OneCompression","owner_avatar_url":"https://avatars.githubusercontent.com/u/89898454?v=4","primary_language":"Python","stars":426,"forks":20,"topics":["llm","qep","quantization","vllm"],"archived":false,"github_pushed_at":"2026-09-14T12:48:55+00:00","maintenance_label":"Very active","stars_delta_30d":28,"url":"https://www.graphcanon.com/tools/fujitsuresearch-onecompression","markdown_url":"https://www.graphcanon.com/tools/fujitsuresearch-onecompression.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fujitsuresearch-onecompression","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fujitsuresearch-onecompression"},"categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"compression","name":"compression"},{"slug":"cuda","name":"cuda"},{"slug":"llm","name":"llm"},{"slug":"mps","name":"mps"},{"slug":"pytorch","name":"pytorch"},{"slug":"qep","name":"qep"},{"slug":"quantization","name":"quantization"},{"slug":"vllm","name":"vllm"}],"edges":[],"neighbours":[{"slug":"headroomlabs-ai-headroom","name":"headroom","tagline":"Compress tool outputs, logs, files, and RAG chunks before they reach the LLM.","github_url":"https://github.com/headroomlabs-ai/headroom","owner":"headroomlabs-ai","repo":"headroom","owner_avatar_url":"https://avatars.githubusercontent.com/u/294291659?v=4","primary_language":"Python","stars":72850,"forks":5600,"topics":["agent","ai","anthropic","claude-code","compression","context-engineering","context-window","cursor","fastapi","langchain","llm","mcp","openai","prompt-engineering","proxy","python","rag","token-optimization","tokens","typescript"],"archived":false,"github_pushed_at":"2026-09-17T23:57:28+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/headroomlabs-ai-headroom","markdown_url":"https://www.graphcanon.com/tools/headroomlabs-ai-headroom.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/headroomlabs-ai-headroom","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=headroomlabs-ai-headroom","shared_categories":["model-training","inference-serving"]},{"slug":"bitsandbytes-foundation-bitsandbytes","name":"bitsandbytes","tagline":"Large language model quantization toolkit for PyTorch.","github_url":"https://github.com/bitsandbytes-foundation/bitsandbytes","owner":"bitsandbytes-foundation","repo":"bitsandbytes","owner_avatar_url":"https://avatars.githubusercontent.com/u/175231607?v=4","primary_language":"Python","stars":8507,"forks":938,"topics":["llm","machine-learning","pytorch","qlora","quantization"],"archived":false,"github_pushed_at":"2026-09-07T14:36:23+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/bitsandbytes-foundation-bitsandbytes","markdown_url":"https://www.graphcanon.com/tools/bitsandbytes-foundation-bitsandbytes.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bitsandbytes-foundation-bitsandbytes","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bitsandbytes-foundation-bitsandbytes","shared_categories":["llm-frameworks","inference-serving"]},{"slug":"huangowen-awesome-llm-compression","name":"Awesome-LLM-Compression","tagline":"Awesome LLM compression research papers and tools to accelerate LLM training and inference.","github_url":"https://github.com/HuangOwen/Awesome-LLM-Compression","owner":"HuangOwen","repo":"Awesome-LLM-Compression","owner_avatar_url":"https://avatars.githubusercontent.com/u/24937399?v=4","primary_language":null,"stars":1883,"forks":134,"topics":[],"archived":false,"github_pushed_at":"2026-08-27T15:48:21+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/huangowen-awesome-llm-compression","markdown_url":"https://www.graphcanon.com/tools/huangowen-awesome-llm-compression.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huangowen-awesome-llm-compression","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huangowen-awesome-llm-compression","shared_categories":["llm-frameworks","inference-serving"]},{"slug":"zlab-princeton-llm-pruning-collection","name":"llm-pruning-collection","tagline":"Collection of LLM pruning methods and training code for GPUs & TPUs.","github_url":"https://github.com/zlab-princeton/llm-pruning-collection","owner":"zlab-princeton","repo":"llm-pruning-collection","owner_avatar_url":"https://avatars.githubusercontent.com/u/237910146?v=4","primary_language":"Python","stars":72,"forks":9,"topics":["jax","llm-evaluation","llm-training","pruning","pruning-models","tpu"],"archived":false,"github_pushed_at":"2026-04-20T18:15:44+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/zlab-princeton-llm-pruning-collection","markdown_url":"https://www.graphcanon.com/tools/zlab-princeton-llm-pruning-collection.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zlab-princeton-llm-pruning-collection","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zlab-princeton-llm-pruning-collection","shared_categories":["model-training"]}]}}