microsoft / ParrotServe
[OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
☆154Updated 7 months ago
Alternatives and similar repositories for ParrotServe:
Users that are interested in ParrotServe are comparing it to the libraries listed below
- Stateful LLM Serving☆63Updated last month
- ☆59Updated 10 months ago
- ☆95Updated 5 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆116Updated last year
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆246Updated last month
- ☆104Updated 3 months ago
- High performance Transformer implementation in C++.☆118Updated 3 months ago
- ☆98Updated 6 months ago
- nnScaler: Compiling DNN models for Parallel Training☆107Updated last week
- LLM Serving Performance Evaluation Harness☆77Updated 2 months ago
- A resilient distributed training framework☆94Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆163Updated 6 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆162Updated 9 months ago
- Summary of some awesome work for optimizing LLM inference☆69Updated last week
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆85Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆46Updated 5 months ago
- ☆45Updated 9 months ago
- Modular and structured prompt caching for low-latency LLM inference☆91Updated 5 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆34Updated last week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆171Updated this week
- DeepSeek-V3/R1 inference performance simulator☆113Updated 3 weeks ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated 10 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆354Updated last week
- ☆82Updated 3 years ago
- A low-latency & high-throughput serving engine for LLMs☆346Updated last week
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆81Updated last year
- Perplexity GPU Kernels☆251Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆305Updated 9 months ago
- LLM serving cluster simulator☆97Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆115Updated 4 months ago