li-plus / flash-preferenceLinks
Accelerate LLM preference tuning via prefix sharing with a single line of code
☆43Updated last month
Alternatives and similar repositories for flash-preference
Users that are interested in flash-preference are comparing it to the libraries listed below
Sorting:
- Odysseus: Playground of LLM Sequence Parallelism☆76Updated last year
- Quantized Attention on GPU☆44Updated 9 months ago
- ☆50Updated 3 months ago
- ☆123Updated 2 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆113Updated 2 months ago
- ☆77Updated 3 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆47Updated last year
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆160Updated 2 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆133Updated 3 months ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆51Updated last month
- ☆44Updated 3 weeks ago
- Efficient Attention Methods: A Comprehensive Survey☆75Updated this week
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆48Updated this week
- ☆91Updated last week
- ☆38Updated 2 weeks ago
- 16-fold memory access reduction with nearly no loss☆104Updated 5 months ago
- ☆61Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- patches for huggingface transformers to save memory☆27Updated 2 months ago
- Transformers components but in Triton☆34Updated 3 months ago
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆32Updated 8 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆81Updated last week
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆145Updated last month
- Beyond KV Caching: Shared Attention for Efficient LLMs☆19Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆125Updated 8 months ago
- ☆80Updated 6 months ago
- Estimate MFU for DeepSeekV3☆24Updated 7 months ago
- DeeperGEMM: crazy optimized version☆71Updated 3 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆76Updated last month