{"data":{"node":{"slug":"feifeibear-long-context-attention","name":"long-context-attention","tagline":"Unified Sequence Parallel Attention for Long Context Transformers","github_url":"https://github.com/feifeibear/long-context-attention","owner":"feifeibear","repo":"long-context-attention","owner_avatar_url":"https://avatars.githubusercontent.com/u/5706969?v=4","primary_language":"Python","stars":693,"forks":85,"topics":["attention-is-all-you-need","deepspeed-ulysses","llm-inference","llm-training","pytorch","ring-attention"],"archived":false,"github_pushed_at":"2026-09-16T06:06:29+00:00","maintenance_label":"Very active","stars_delta_30d":11,"url":"https://www.graphcanon.com/tools/feifeibear-long-context-attention","markdown_url":"https://www.graphcanon.com/tools/feifeibear-long-context-attention.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/feifeibear-long-context-attention","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=feifeibear-long-context-attention"},"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":"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":"attention-is-all-you-need","name":"attention-is-all-you-need"},{"slug":"deepspeed-ulysses","name":"deepspeed-ulysses"},{"slug":"llm-inference","name":"llm-inference"},{"slug":"llm-training","name":"llm-training"},{"slug":"pytorch","name":"pytorch"},{"slug":"ring-attention","name":"ring-attention"}],"edges":[],"neighbours":[{"slug":"huggingface-peft","name":"peft","tagline":"State-of-the-art Parameter-Efficient Fine-Tuning","github_url":"https://github.com/huggingface/peft","owner":"huggingface","repo":"peft","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":21704,"forks":2511,"topics":["adapter","diffusion","fine-tuning","llm","lora","parameter-efficient-learning","peft","python","pytorch","transformers"],"archived":false,"github_pushed_at":"2026-09-18T13:30:46+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-peft","markdown_url":"https://www.graphcanon.com/tools/huggingface-peft.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-peft","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-peft","shared_categories":["model-training"]},{"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":["inference-serving"]},{"slug":"ymcui-chinese-llama-alpaca-2","name":"Chinese-LLaMA-Alpaca-2","tagline":"Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models","github_url":"https://github.com/ymcui/Chinese-LLaMA-Alpaca-2","owner":"ymcui","repo":"Chinese-LLaMA-Alpaca-2","owner_avatar_url":"https://avatars.githubusercontent.com/u/16095339?v=4","primary_language":"Python","stars":7118,"forks":559,"topics":["64k","alpaca","alpaca-2","alpaca2","flash-attention","large-language-models","llama","llama-2","llama2","llm","nlp","rlhf","yarn"],"archived":false,"github_pushed_at":"2026-04-19T00:58:50+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/ymcui-chinese-llama-alpaca-2","markdown_url":"https://www.graphcanon.com/tools/ymcui-chinese-llama-alpaca-2.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ymcui-chinese-llama-alpaca-2","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ymcui-chinese-llama-alpaca-2","shared_categories":["model-training","inference-serving"]},{"slug":"linkedin-liger-kernel","name":"Liger-Kernel","tagline":"Efficient Triton Kernels for LLM Training","github_url":"https://github.com/linkedin/Liger-Kernel","owner":"linkedin","repo":"Liger-Kernel","owner_avatar_url":"https://avatars.githubusercontent.com/u/357098?v=4","primary_language":"Python","stars":6600,"forks":593,"topics":["finetuning","gemma2","hacktoberfest","llama","llama3","llm-training","llms","mistral","phi3","triton","triton-kernels"],"archived":false,"github_pushed_at":"2026-09-03T15:56:18+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/linkedin-liger-kernel","markdown_url":"https://www.graphcanon.com/tools/linkedin-liger-kernel.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/linkedin-liger-kernel","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=linkedin-liger-kernel","shared_categories":["model-training"]},{"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":"Cuda","stars":6452,"forks":1472,"topics":["attention","cuda","distributed-inference","gpu","jit","large-large-models","llm-inference","moe","nvidia","pytorch"],"archived":false,"github_pushed_at":"2026-09-19T01:31:07+00:00","maintenance_label":"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":"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":6448,"forks":934,"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":"fla-org-flash-linear-attention","name":"flash-linear-attention","tagline":"🚀 Efficient implementations for emerging model architectures","github_url":"https://github.com/fla-org/flash-linear-attention","owner":"fla-org","repo":"flash-linear-attention","owner_avatar_url":"https://avatars.githubusercontent.com/u/40835596?v=4","primary_language":"Python","stars":5568,"forks":661,"topics":["large-language-models","machine-learning-systems","natural-language-processing","sequence-modeling"],"archived":false,"github_pushed_at":"2026-08-17T10:13:08+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/fla-org-flash-linear-attention","markdown_url":"https://www.graphcanon.com/tools/fla-org-flash-linear-attention.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fla-org-flash-linear-attention","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fla-org-flash-linear-attention","shared_categories":["model-training"]},{"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":5508,"forks":435,"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":"Steady","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":"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":2773,"forks":205,"topics":["llm","llm-inference"],"archived":false,"github_pushed_at":"2024-06-25T12:23:04+00:00","maintenance_label":"Dormant","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","shared_categories":["inference-serving"]},{"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":2080,"forks":212,"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":["model-training"]},{"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":["inference-serving"]},{"slug":"thudm-longwriter","name":"LongWriter","tagline":"LongWriter enables generation of texts longer than 10,000 words using long-context LLMs","github_url":"https://github.com/THUDM/LongWriter","owner":"THUDM","repo":"LongWriter","owner_avatar_url":"https://avatars.githubusercontent.com/u/48590610?v=4","primary_language":"Python","stars":1876,"forks":182,"topics":["fine-tuning","llm","long-context","long-text"],"archived":false,"github_pushed_at":"2025-06-24T06:41:41+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/thudm-longwriter","markdown_url":"https://www.graphcanon.com/tools/thudm-longwriter.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/thudm-longwriter","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=thudm-longwriter","shared_categories":["model-training"]}]}}