{"data":{"node":{"slug":"fasterdecoding-medusa","name":"Medusa","tagline":"Framework for accelerating LLM generation using multiple decoding heads","github_url":"https://github.com/FasterDecoding/Medusa","owner":"FasterDecoding","repo":"Medusa","owner_avatar_url":"https://avatars.githubusercontent.com/u/144572371?v=4","primary_language":"Jupyter Notebook","stars":2767,"forks":205,"topics":["llm","llm-inference"],"archived":false,"github_pushed_at":"2024-06-25T12:23:04+00:00","maintenance_label":"Dormant","stars_delta_30d":9,"url":"https://www.graphcanon.com/tools/fasterdecoding-medusa","markdown_url":"https://www.graphcanon.com/tools/fasterdecoding-medusa.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fasterdecoding-medusa","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fasterdecoding-medusa"},"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"}],"tags":[{"slug":"acceleration","name":"acceleration"},{"slug":"decoding","name":"decoding"},{"slug":"inference","name":"inference"},{"slug":"llm","name":"llm"}],"edges":[],"neighbours":[{"slug":"bradyfu-awesome-multimodal-large-language-models","name":"Awesome-Multimodal-Large-Language-Models","tagline":"Latest Advances on Multimodal Large Language Models","github_url":"https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models","owner":"BradyFU","repo":"Awesome-Multimodal-Large-Language-Models","owner_avatar_url":"https://avatars.githubusercontent.com/u/54254631?v=4","primary_language":null,"stars":17978,"forks":1133,"topics":["chain-of-thought","in-context-learning","instruction-following","instruction-tuning","large-language-models","large-vision-language-model","large-vision-language-models","multi-modality","multimodal-chain-of-thought","multimodal-in-context-learning","multimodal-instruction-tuning","multimodal-large-language-models","visual-instruction-tuning"],"archived":false,"github_pushed_at":"2026-08-14T17:17:50+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/bradyfu-awesome-multimodal-large-language-models","markdown_url":"https://www.graphcanon.com/tools/bradyfu-awesome-multimodal-large-language-models.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bradyfu-awesome-multimodal-large-language-models","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bradyfu-awesome-multimodal-large-language-models","shared_categories":[]},{"slug":"lightning-ai-litgpt","name":"litgpt","tagline":"High-performance LLMs with recipes for pretraining, finetuning and deployment","github_url":"https://github.com/Lightning-AI/litgpt","owner":"Lightning-AI","repo":"litgpt","owner_avatar_url":"https://avatars.githubusercontent.com/u/58386951?v=4","primary_language":"Python","stars":13605,"forks":1483,"topics":["ai","artificial-intelligence","deep-learning","large-language-models","llm","llm-inference","llms"],"archived":false,"github_pushed_at":"2026-07-20T10:24:12+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/lightning-ai-litgpt","markdown_url":"https://www.graphcanon.com/tools/lightning-ai-litgpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lightning-ai-litgpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lightning-ai-litgpt","shared_categories":["inference-serving"]},{"slug":"ericlbuehler-mistral-rs","name":"mistral.rs","tagline":"Fast flexible LLM inference","github_url":"https://github.com/EricLBuehler/mistral.rs","owner":"EricLBuehler","repo":"mistral.rs","owner_avatar_url":"https://avatars.githubusercontent.com/u/65165915?v=4","primary_language":"Rust","stars":7575,"forks":671,"topics":["llm","rust","uqff"],"archived":false,"github_pushed_at":"2026-07-29T20:21:17+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/ericlbuehler-mistral-rs","markdown_url":"https://www.graphcanon.com/tools/ericlbuehler-mistral-rs.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ericlbuehler-mistral-rs","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ericlbuehler-mistral-rs","shared_categories":["inference-serving"]},{"slug":"eleutherai-gpt-neox","name":"gpt-neox","tagline":"Implementation of model parallel autoregressive transformers on GPUs based on Megatron and DeepSpeed libraries","github_url":"https://github.com/EleutherAI/gpt-neox","owner":"EleutherAI","repo":"gpt-neox","owner_avatar_url":"https://avatars.githubusercontent.com/u/68924597?v=4","primary_language":"Python","stars":7452,"forks":1119,"topics":["deepspeed-library","gpt-3","language-model","transformers"],"archived":false,"github_pushed_at":"2026-06-11T19:25:44+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/eleutherai-gpt-neox","markdown_url":"https://www.graphcanon.com/tools/eleutherai-gpt-neox.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eleutherai-gpt-neox","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eleutherai-gpt-neox","shared_categories":[]},{"slug":"nvidia-fastertransformer","name":"FasterTransformer","tagline":"Transformer related optimization including BERT and GPT","github_url":"https://github.com/NVIDIA/FasterTransformer","owner":"NVIDIA","repo":"FasterTransformer","owner_avatar_url":"https://avatars.githubusercontent.com/u/1728152?v=4","primary_language":"C++","stars":6446,"forks":935,"topics":["bert","gpt","pytorch","transformer"],"archived":false,"github_pushed_at":"2024-03-27T11:25:30+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/nvidia-fastertransformer","markdown_url":"https://www.graphcanon.com/tools/nvidia-fastertransformer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nvidia-fastertransformer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nvidia-fastertransformer","shared_categories":["inference-serving"]},{"slug":"flashinfer-ai-flashinfer","name":"flashinfer","tagline":"FlashInfer is a kernel library for serving large language models","github_url":"https://github.com/flashinfer-ai/flashinfer","owner":"flashinfer-ai","repo":"flashinfer","owner_avatar_url":"https://avatars.githubusercontent.com/u/145061914?v=4","primary_language":"Python","stars":6231,"forks":1327,"topics":["attention","cuda","distributed-inference","gpu","jit","large-large-models","llm-inference","moe","nvidia","pytorch"],"archived":false,"github_pushed_at":"2026-08-24T17:00:11+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/flashinfer-ai-flashinfer","markdown_url":"https://www.graphcanon.com/tools/flashinfer-ai-flashinfer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/flashinfer-ai-flashinfer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=flashinfer-ai-flashinfer","shared_categories":["inference-serving"]},{"slug":"xlite-dev-awesome-llm-inference","name":"Awesome-LLM-Inference","tagline":"A curated list of LLM/VLM inference papers with codes","github_url":"https://github.com/xlite-dev/Awesome-LLM-Inference","owner":"xlite-dev","repo":"Awesome-LLM-Inference","owner_avatar_url":"https://avatars.githubusercontent.com/u/204302598?v=4","primary_language":"Python","stars":5477,"forks":429,"topics":["awesome-llm","deepseek","deepseek-r1","deepseek-v3","flash-attention","flash-attention-3","flash-mla","llm-inference","minimax-01","mla","paged-attention","qwen3","tensorrt-llm","vllm"],"archived":false,"github_pushed_at":"2026-08-14T12:23:49+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/xlite-dev-awesome-llm-inference","markdown_url":"https://www.graphcanon.com/tools/xlite-dev-awesome-llm-inference.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/xlite-dev-awesome-llm-inference","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=xlite-dev-awesome-llm-inference","shared_categories":["inference-serving"]},{"slug":"eth-sri-lmql","name":"lmql","tagline":"A language for constraint-guided and efficient LLM programming.","github_url":"https://github.com/eth-sri/lmql","owner":"eth-sri","repo":"lmql","owner_avatar_url":"https://avatars.githubusercontent.com/u/5363413?v=4","primary_language":"Python","stars":4203,"forks":221,"topics":["chatgpt","huggingface","language-model","programming-language"],"archived":false,"github_pushed_at":"2025-05-22T07:32:31+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/eth-sri-lmql","markdown_url":"https://www.graphcanon.com/tools/eth-sri-lmql.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eth-sri-lmql","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eth-sri-lmql","shared_categories":[]},{"slug":"eladlev-autoprompt","name":"AutoPrompt","tagline":"Framework for prompt tuning using Intent-based Prompt Calibration","github_url":"https://github.com/Eladlev/AutoPrompt","owner":"Eladlev","repo":"AutoPrompt","owner_avatar_url":"https://avatars.githubusercontent.com/u/28984104?v=4","primary_language":"Python","stars":2993,"forks":264,"topics":["prompt-engineering","prompt-tuning","synthetic-dataset-generation"],"archived":false,"github_pushed_at":"2025-12-02T17:23:20+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/eladlev-autoprompt","markdown_url":"https://www.graphcanon.com/tools/eladlev-autoprompt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eladlev-autoprompt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eladlev-autoprompt","shared_categories":[]},{"slug":"thudm-p-tuning-v2","name":"P-tuning-v2","tagline":"Optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks","github_url":"https://github.com/THUDM/P-tuning-v2","owner":"THUDM","repo":"P-tuning-v2","owner_avatar_url":"https://avatars.githubusercontent.com/u/48590610?v=4","primary_language":"Python","stars":2077,"forks":213,"topics":["natural-language-processing","p-tuning","parameter-efficient-learning","pretrained-language-model","prompt-tuning"],"archived":false,"github_pushed_at":"2023-11-16T04:38:09+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/thudm-p-tuning-v2","markdown_url":"https://www.graphcanon.com/tools/thudm-p-tuning-v2.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/thudm-p-tuning-v2","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=thudm-p-tuning-v2","shared_categories":[]},{"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":1859,"forks":129,"topics":[],"archived":false,"github_pushed_at":"2026-06-30T15:26:46+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":["inference-serving"]},{"slug":"sakanaai-text-to-lora","name":"text-to-lora","tagline":"Hypernetworks for adapting LLMs to specific tasks via textual descriptions","github_url":"https://github.com/SakanaAI/text-to-lora","owner":"SakanaAI","repo":"text-to-lora","owner_avatar_url":"https://avatars.githubusercontent.com/u/140988036?v=4","primary_language":"Python","stars":1300,"forks":88,"topics":["fine-tuning","hypernetworks","llm","lora","machine-learning"],"archived":false,"github_pushed_at":"2025-06-08T14:42:10+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/sakanaai-text-to-lora","markdown_url":"https://www.graphcanon.com/tools/sakanaai-text-to-lora.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sakanaai-text-to-lora","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sakanaai-text-to-lora","shared_categories":[]}]}}