bytedance / ShadowKV
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
☆151Updated 4 months ago
Alternatives and similar repositories for ShadowKV:
Users that are interested in ShadowKV are comparing it to the libraries listed below
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆240Updated 6 months ago
- Official Code for "SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression"☆135Updated last month
- MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction☆80Updated 4 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆67Updated last month
- 16-fold memory access reduction with nearly no loss☆80Updated 3 weeks ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆253Updated 3 months ago
- ☆52Updated 11 months ago
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆216Updated 5 months ago
- ☆88Updated this week
- A sparse attention kernel supporting mix sparse patterns☆159Updated last month
- ☆229Updated 10 months ago
- Support mixed-precsion inference with vllm☆80Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 8 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆144Updated 8 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆82Updated last year
- ☆58Updated 5 months ago
- [ICLR 2025] PEARL: parallel speculative decoding with adaptive draft length☆52Updated this week
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆85Updated 3 weeks ago
- Quantized Attention on GPU☆45Updated 3 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆41Updated 4 months ago
- ☆115Updated 3 weeks ago
- ☆44Updated 3 months ago
- Implement some method of LLM KV Cache Sparsity☆30Updated 9 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆29Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆109Updated 3 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆42Updated 7 months ago
- ☆38Updated 3 months ago
- ☆29Updated 7 months ago
- ☆63Updated 3 months ago