LINs-lab / DeFTLinks
[ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference
☆48Updated 7 months ago
Alternatives and similar repositories for DeFT
Users that are interested in DeFT are comparing it to the libraries listed below
Sorting:
- ☆220Updated 2 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆128Updated last month
- Quantized Attention on GPU☆44Updated last year
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆115Updated 2 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆128Updated 7 months ago
- 16-fold memory access reduction with nearly no loss☆109Updated 10 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆44Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 6 months ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆81Updated last month
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆161Updated 3 months ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆69Updated 6 months ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆46Updated 3 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆52Updated 5 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆67Updated last year
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆86Updated last month
- ☆50Updated 8 months ago
- ☆52Updated 8 months ago
- ☆39Updated 5 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆48Updated last year
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆56Updated last year
- Distributed MoE in a Single Kernel [NeurIPS '25]☆188Updated this week
- ☆64Updated last year
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆73Updated 6 months ago
- Dynamic Context Selection for Efficient Long-Context LLMs☆54Updated 8 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆39Updated 11 months ago
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆274Updated last month
- Beyond KV Caching: Shared Attention for Efficient LLMs☆20Updated last year
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆80Updated 3 weeks ago
- Kinetics: Rethinking Test-Time Scaling Laws☆85Updated 6 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year