yale-sys / prompt-cacheLinks
Modular and structured prompt caching for low-latency LLM inference
☆103Updated last year
Alternatives and similar repositories for prompt-cache
Users that are interested in prompt-cache are comparing it to the libraries listed below
Sorting:
- LLM Serving Performance Evaluation Harness☆81Updated 9 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆199Updated last year
- ☆141Updated last year
- ☆152Updated 4 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆132Updated 11 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆94Updated 2 years ago
- ☆83Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆132Updated last year
- Stateful LLM Serving☆89Updated 8 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆243Updated last year
- KV cache compression for high-throughput LLM inference☆143Updated 9 months ago
- ☆82Updated 7 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆207Updated 6 months ago
- ☆48Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆262Updated last month
- A low-latency & high-throughput serving engine for LLMs☆447Updated last month
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆64Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆170Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆103Updated 2 months ago
- ☆124Updated last year
- ☆88Updated 3 years ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆241Updated 11 months ago
- ☆79Updated last month
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆112Updated 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 …☆292Updated 5 months ago
- ☆290Updated 4 months ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆28Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆331Updated last year
- A large-scale simulation framework for LLM inference☆485Updated 4 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆212Updated 2 months ago