EfficientMoE / MoE-InfinityLinks
PyTorch library for cost-effective, fast and easy serving of MoE models.
☆252Updated last week
Alternatives and similar repositories for MoE-Infinity
Users that are interested in MoE-Infinity are comparing it to the libraries listed below
Sorting:
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆221Updated 2 years ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆278Updated 4 months ago
- nnScaler: Compiling DNN models for Parallel Training☆118Updated last month
- A low-latency & high-throughput serving engine for LLMs☆431Updated last week
- ☆74Updated last week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆338Updated 3 months ago
- ☆141Updated 3 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆186Updated last year
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆237Updated 11 months ago
- ☆124Updated 11 months ago
- High performance Transformer implementation in C++.☆138Updated 9 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆278Updated 7 months ago
- A large-scale simulation framework for LLM inference☆459Updated 2 months ago
- ☆341Updated last year
- Stateful LLM Serving☆87Updated 7 months ago
- A lightweight design for computation-communication overlap.☆181Updated 2 weeks ago
- ☆136Updated last year
- Latency and Memory Analysis of Transformer Models for Training and Inference☆459Updated 6 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆439Updated this week
- ☆307Updated 3 weeks ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆92Updated 2 years ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆30Updated last year
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆75Updated 4 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 3 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆213Updated 3 months ago
- Allow torch tensor memory to be released and resumed later☆150Updated this week
- Summary of some awesome work for optimizing LLM inference☆120Updated 4 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆155Updated last year
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago