li-plus / flash-preferenceLinks
Accelerate LLM preference tuning via prefix sharing with a single line of code
☆43Updated 3 months ago
Alternatives and similar repositories for flash-preference
Users that are interested in flash-preference are comparing it to the libraries listed below
Sorting:
- ☆50Updated 4 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆77Updated last year
- Quantized Attention on GPU☆44Updated 10 months ago
- ☆129Updated 4 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆118Updated 3 months ago
- ☆98Updated 4 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆71Updated last week
- Estimate MFU for DeepSeekV3☆24Updated 9 months ago
- Transformers components but in Triton☆34Updated 4 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆143Updated 4 months ago
- ☆39Updated last month
- ☆64Updated 5 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- Fast and memory-efficient exact kmeans☆91Updated this week
- ☆55Updated this week
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆40Updated 3 weeks ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆50Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆189Updated 3 months ago
- ☆142Updated 7 months ago
- DeeperGEMM: crazy optimized version☆71Updated 5 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆128Updated 10 months ago
- ☆112Updated last month
- Beyond KV Caching: Shared Attention for Efficient LLMs☆19Updated last year
- Framework to reduce autotune overhead to zero for well known deployments.☆84Updated 2 weeks ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆49Updated 11 months ago
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated last month
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆146Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- patches for huggingface transformers to save memory☆28Updated 4 months ago