HugoZHL / PQCacheLinks
[SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inference
☆55Updated last week
Alternatives and similar repositories for PQCache
Users that are interested in PQCache are comparing it to the libraries listed below
Sorting:
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆52Updated last week
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆138Updated 11 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆40Updated 6 months ago
- ☆103Updated 7 months ago
- ☆121Updated 5 months ago
- ☆62Updated last year
- This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding co…☆154Updated this week
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆39Updated last week
- ☆54Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆26Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆163Updated 9 months ago
- Stateful LLM Serving☆73Updated 3 months ago
- ☆109Updated 8 months ago
- High performance Transformer implementation in C++.☆125Updated 5 months ago
- ☆67Updated 8 months ago
- ☆18Updated 3 months ago
- ☆72Updated 3 years ago
- Query-Adaptive Vector Search☆35Updated 2 weeks ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆9Updated last year
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆79Updated 5 months ago
- GPU-accelerated vector query processing system that supports large vector datasets beyond GPU memory.☆28Updated last year
- Implement some method of LLM KV Cache Sparsity☆32Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆89Updated 2 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆88Updated 2 years ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆48Updated 7 months ago
- ☆32Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated 2 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆177Updated 8 months ago
- An experimentation platform for LLM inference optimisation☆31Updated 9 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆214Updated last year