z-lab / flash-colreduceLinks
Fast, memory-efficient attention column reduction (e.g., sum, mean, max)
☆34Updated this week
Alternatives and similar repositories for flash-colreduce
Users that are interested in flash-colreduce are comparing it to the libraries listed below
Sorting:
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆269Updated 7 months ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆70Updated 7 months ago
- A sparse attention kernel supporting mix sparse patterns☆453Updated 3 weeks ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆160Updated 3 months ago
- ☆221Updated 2 months ago
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆278Updated 2 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆131Updated 2 months ago
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆87Updated 2 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆197Updated 2 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆825Updated 2 weeks ago
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆32Updated 10 months ago
- A record of reading list on some MLsys popular topic☆21Updated 10 months ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆87Updated 2 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆126Updated 2 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆192Updated 4 months ago
- Building the Virtuous Cycle for AI-driven LLM Systems☆151Updated last week
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆61Updated 4 months ago
- d3LLM: Ultra-Fast Diffusion LLM 🚀☆90Updated this week
- 16-fold memory access reduction with nearly no loss☆110Updated 10 months ago
- Code for the paper “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling”☆118Updated last week
- ☆64Updated last year
- ☆24Updated last month
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆260Updated 3 weeks ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆25Updated last year
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆149Updated 10 months ago
- [NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.☆180Updated last year
- [NeurIPS'25] dKV-Cache: The Cache for Diffusion Language Models☆129Updated 8 months ago
- [ICML 2025] SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆51Updated last year
- [ICLR 2025] Mixture Compressor for Mixture-of-Experts LLMs Gains More☆66Updated 11 months ago
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆69Updated 3 weeks ago