SakanaAI / L2DLinks
Large language models to diffusion finetuning code
☆23Updated 8 months ago
Alternatives and similar repositories for L2D
Users that are interested in L2D are comparing it to the libraries listed below
Sorting:
- Transformers components but in Triton☆34Updated 9 months ago
- ☆54Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆141Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆93Updated last year
- Official implementation for Training LLMs with MXFP4☆118Updated 9 months ago
- Fast and memory-efficient exact attention☆75Updated 11 months ago
- The evaluation framework for training-free sparse attention in LLMs☆117Updated 2 weeks ago
- Code for studying the super weight in LLM☆121Updated last year
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆87Updated last week
- Make reasoning models scalable☆47Updated 8 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆88Updated 10 months ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆45Updated 3 weeks ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆176Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆21Updated last year
- ☆77Updated last week
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆114Updated 10 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆131Updated last year
- Muon fsdp 2☆53Updated 6 months ago
- ☆31Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆157Updated 10 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆53Updated 6 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆86Updated 7 months ago
- ☆45Updated 2 years ago
- ☆15Updated 6 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆128Updated 7 months ago
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆69Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆92Updated 6 months ago
- ☆63Updated 7 months ago