PiotrNawrot / sparse-frontierLinks
The evaluation framework for training-free sparse attention in LLMs
☆106Updated 2 months ago
Alternatives and similar repositories for sparse-frontier
Users that are interested in sparse-frontier are comparing it to the libraries listed below
Sorting:
- ☆133Updated 6 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆126Updated 5 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆223Updated 6 months ago
- Fast and memory-efficient exact attention☆75Updated 9 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆91Updated 5 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆131Updated last year
- ☆156Updated 10 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- ☆101Updated 9 months ago
- Official implementation for Training LLMs with MXFP4☆115Updated 7 months ago
- [ICML 2025] From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications☆52Updated last month
- Kinetics: Rethinking Test-Time Scaling Laws☆84Updated 5 months ago
- Work in progress.☆75Updated 3 weeks ago
- ☆113Updated last month
- Muon fsdp 2☆46Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆172Updated last year
- Code for studying the super weight in LLM☆121Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆159Updated 2 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆107Updated last month
- ☆60Updated 6 months ago
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆18Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆146Updated last year
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- ☆54Updated last year
- ☆259Updated 6 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆89Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆135Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆257Updated 2 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 5 months ago
- Memory optimized Mixture of Experts☆72Updated 4 months ago