interestingLSY / swiftLLMLinks
A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).
☆267Updated 3 months ago
Alternatives and similar repositories for swiftLLM
Users that are interested in swiftLLM are comparing it to the libraries listed below
Sorting:
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆273Updated 6 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆241Updated 2 months ago
- High performance Transformer implementation in C++.☆134Updated 8 months ago
- Summary of some awesome work for optimizing LLM inference☆111Updated 3 months ago
- ☆123Updated 10 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆421Updated 4 months ago
- ☆147Updated 6 months ago
- ☆138Updated 2 months ago
- paper and its code for AI System☆330Updated last month
- This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding co…☆212Updated 2 months ago
- A lightweight design for computation-communication overlap.☆177Updated 2 weeks ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆404Updated last week
- Allow torch tensor memory to be released and resumed later☆142Updated last week
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆154Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆184Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆339Updated 2 months ago
- ☆72Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆118Updated last week
- A low-latency & high-throughput serving engine for LLMs☆422Updated 4 months ago
- ☆56Updated last year
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆41Updated last week
- ☆42Updated last year
- Curated collection of papers in MoE model inference☆270Updated 2 weeks ago
- A large-scale simulation framework for LLM inference☆452Updated 2 months ago
- Stateful LLM Serving☆85Updated 6 months ago
- ☆77Updated 11 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆72Updated 3 months ago
- This repository is established to store personal notes and annotated papers during daily research.☆152Updated last month
- ☆298Updated last week
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆94Updated this week