amazon-science / piperag
PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design
☆11Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for piperag
- ☆42Updated 5 months ago
- Stateful LLM Serving☆37Updated 3 months ago
- ☆51Updated last month
- Modular and structured prompt caching for low-latency LLM inference☆65Updated this week
- ☆43Updated last month
- ☆63Updated last month
- MagicPIG: LSH Sampling for Efficient LLM Generation☆45Updated 2 weeks ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆111Updated last month
- A resilient distributed training framework☆85Updated 7 months ago
- Materials for learning SGLang☆86Updated this week
- An Attention Superoptimizer☆20Updated 6 months ago
- ☆17Updated 4 months ago
- TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆21Updated last month
- A minimal implementation of vllm.☆30Updated 3 months ago
- LLM Serving Performance Evaluation Harness☆55Updated 2 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆74Updated last year
- Sequence-level 1F1B schedule for LLMs.☆17Updated 5 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆101Updated 2 months ago
- Quantized Attention on GPU☆29Updated last week
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆178Updated last year
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆99Updated 8 months ago
- ☆36Updated 4 months ago
- ☆36Updated last month
- ☆42Updated 7 months ago
- ☆34Updated 2 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆98Updated 4 months ago
- ☆70Updated 2 years ago
- ☆63Updated 3 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆126Updated 3 weeks ago
- Python package for rematerialization-aware gradient checkpointing☆23Updated last year