LMCache / demoLinks
☆23Updated 4 months ago
Alternatives and similar repositories for demo
Users that are interested in demo are comparing it to the libraries listed below
Sorting:
- Modular and structured prompt caching for low-latency LLM inference☆99Updated 9 months ago
- The driver for LMCache core to run in vLLM☆48Updated 7 months ago
- ☆47Updated last year
- LLM Serving Performance Evaluation Harness☆79Updated 6 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆125Updated 9 months ago
- ☆79Updated 9 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆181Updated 11 months ago
- ☆69Updated last year
- ☆93Updated 5 months ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆75Updated this week
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆77Updated 2 weeks ago
- KV cache compression for high-throughput LLM inference☆136Updated 7 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆56Updated this week
- ☆132Updated last month
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆30Updated 9 months ago
- ☆16Updated 2 months ago
- Stateful LLM Serving☆81Updated 5 months ago
- Code for MLSys 2024 Paper "SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models"☆21Updated last year
- ☆288Updated last week
- ☆123Updated 10 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆128Updated last year
- ☆31Updated 4 months ago
- ☆74Updated 5 months ago
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆23Updated 3 weeks ago
- LLM-Inference-Bench☆50Updated last month
- Fast and memory-efficient exact attention☆92Updated last week
- KV cache store for distributed LLM inference☆321Updated 3 months ago
- vLLM performance dashboard☆34Updated last year
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆201Updated last week
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆178Updated this week