yale-sys / prompt-cache
Modular and structured prompt caching for low-latency LLM inference
☆69Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for prompt-cache
- LLM Serving Performance Evaluation Harness☆57Updated 2 months ago
- ☆51Updated last month
- ☆68Updated last month
- Materials for learning SGLang☆110Updated this week
- A low-latency & high-throughput serving engine for LLMs☆247Updated 2 months ago
- Making Long-Context LLM Inference 10x Faster and 10x Cheaper☆240Updated this week
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆74Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆114Updated 2 months ago
- ☆38Updated 4 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆102Updated 9 months ago
- ☆56Updated last week
- A large-scale simulation framework for LLM inference☆278Updated this week
- Stateful LLM Serving☆38Updated 3 months ago
- ☆46Updated 5 months ago
- Efficient and easy multi-instance LLM serving☆219Updated this week
- ☆70Updated 2 years ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated this week
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆181Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆103Updated 3 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆203Updated 3 weeks ago
- A resilient distributed training framework☆85Updated 7 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆106Updated 4 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆240Updated last week
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆57Updated last week
- A minimal implementation of vllm.☆30Updated 3 months ago
- Fast Inference of MoE Models with CPU-GPU Orchestration☆173Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆278Updated 4 months ago
- ☆189Updated 6 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- ☆43Updated 6 months ago