PyTorch library for cost-effective, fast and easy serving of MoE models.
☆288Mar 16, 2026Updated this week
Alternatives and similar repositories for MoE-Infinity
Users that are interested in MoE-Infinity are comparing it to the libraries listed below
Sorting:
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆105Dec 15, 2025Updated 3 months ago
- ☆12Jun 29, 2024Updated last year
- Compiler for Dynamic Neural Networks☆45Nov 13, 2023Updated 2 years ago
- Curated collection of papers in MoE model inference☆357Mar 12, 2026Updated last week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆210Sep 21, 2024Updated last year
- A low-latency & high-throughput serving engine for LLMs☆484Jan 8, 2026Updated 2 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆261Nov 18, 2024Updated last year
- ☆306Jul 10, 2025Updated 8 months ago
- ☆58May 4, 2024Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆376Jul 10, 2025Updated 8 months ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆16May 6, 2024Updated last year
- ☆131Nov 11, 2024Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆466May 30, 2025Updated 9 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆320Jun 10, 2025Updated 9 months ago
- Code release for AdapMoE accepted by ICCAD 2024☆36Apr 28, 2025Updated 10 months ago
- ☆20Sep 28, 2024Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,273Aug 28, 2025Updated 6 months ago
- ☆87Oct 17, 2025Updated 5 months ago
- STREAMer: Benchmarking remote volatile and non-volatile memory bandwidth☆17Aug 21, 2023Updated 2 years ago
- ☆47Jun 27, 2024Updated last year
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆490Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆531Feb 10, 2025Updated last year
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆90Jun 16, 2025Updated 9 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆53Aug 6, 2025Updated 7 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- Serverless LLM Serving for Everyone.☆664Mar 6, 2026Updated 2 weeks ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,864Mar 12, 2026Updated last week
- A GPU-driven system framework for scalable AI applications☆124Feb 5, 2025Updated last year
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆81Dec 18, 2025Updated 3 months ago
- ☆231Oct 24, 2025Updated 4 months ago
- Stateful LLM Serving☆97Mar 11, 2025Updated last year
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆56Aug 6, 2025Updated 7 months ago
- A throughput-oriented high-performance serving framework for LLMs☆949Oct 29, 2025Updated 4 months ago
- ☆152Oct 9, 2024Updated last year
- Efficient and easy multi-instance LLM serving☆532Mar 12, 2026Updated last week
- A sparse attention kernel supporting mix sparse patterns☆480Jan 18, 2026Updated 2 months ago
- LLM Serving Performance Evaluation Harness☆83Feb 25, 2025Updated last year
- An interference-aware scheduler for fine-grained GPU sharing☆161Nov 26, 2025Updated 3 months ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,159Updated this week