yale-sys / prompt-cacheLinks
Modular and structured prompt caching for low-latency LLM inference
☆100Updated 10 months ago
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☆79Updated 6 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆183Updated last year
- ☆135Updated 2 months ago
- ☆130Updated 11 months ago
- ☆77Updated 11 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆129Updated last year
- Stateful LLM Serving☆84Updated 6 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆127Updated 9 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆59Updated 10 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆90Updated 2 years ago
- A low-latency & high-throughput serving engine for LLMs☆416Updated 3 months ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆81Updated this week
- ☆47Updated last year
- ☆123Updated 10 months ago
- ☆71Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆238Updated 2 months ago
- ☆78Updated 5 months ago
- KV cache compression for high-throughput LLM inference☆138Updated 7 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆113Updated last year
- A large-scale simulation framework for LLM inference☆443Updated last month
- The driver for LMCache core to run in vLLM☆50Updated 7 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆234Updated 10 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆264Updated 3 months ago
- ☆279Updated 2 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆222Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆111Updated 5 months ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆24Updated last year
- ☆295Updated this week