microsoft / chunk-attentionLinks
☆82Updated 7 months ago
Alternatives and similar repositories for chunk-attention
Users that are interested in chunk-attention are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆131Updated last month
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆63Updated last year
- ☆152Updated 9 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆224Updated 2 years ago
- ☆58Updated last year
- 16-fold memory access reduction with nearly no loss☆108Updated 8 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆170Updated last year
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆55Updated last year
- An easy-to-use package for implementing SmoothQuant for LLMs☆109Updated 7 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆49Updated 3 months ago
- ☆97Updated 8 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆65Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆132Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆131Updated 6 months ago
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- ☆83Updated last year
- ☆102Updated last year
- A simple calculation for LLM MFU.☆50Updated 2 months ago
- ☆65Updated 7 months ago
- ☆83Updated 10 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆116Updated last week
- Implement some method of LLM KV Cache Sparsity☆42Updated last year
- ☆88Updated 3 years ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆94Updated 2 years ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated last year
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆24Updated last year
- Odysseus: Playground of LLM Sequence Parallelism☆78Updated last year
- ATC23 AE☆47Updated 2 years ago
- ☆290Updated 4 months ago
- ☆124Updated last year