amazon-science / piperag
PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)
☆11Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for piperag
- Stateful LLM Serving☆38Updated 3 months ago
- ☆46Updated 5 months ago
- ☆51Updated last month
- MagicPIG: LSH Sampling for Efficient LLM Generation☆59Updated 3 weeks ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆74Updated last year
- Modular and structured prompt caching for low-latency LLM inference☆68Updated last week
- ☆67Updated last month
- ☆38Updated 4 months ago
- ☆55Updated last week
- An Attention Superoptimizer☆20Updated 6 months ago
- LLM Serving Performance Evaluation Harness☆56Updated 2 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆103Updated 3 months ago
- A resilient distributed training framework☆85Updated 7 months ago
- ☆42Updated 7 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆101Updated 8 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆114Updated 2 months ago
- Materials for learning SGLang☆105Updated this week
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated this week
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆57Updated this week
- Version of PBBS Benchmarks for VLDB 2024 Reviewers☆9Updated last year
- ☆17Updated 4 months ago
- A minimal implementation of vllm.☆30Updated 3 months ago
- Quantized Attention on GPU☆30Updated 2 weeks ago
- Python package for rematerialization-aware gradient checkpointing☆23Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆147Updated 4 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆104Updated 4 months ago
- ☆70Updated 2 years ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆34Updated 8 months ago
- Code for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆16Updated last month
- ☆19Updated 8 months ago