PyTorch library for cost-effective, fast and easy serving of MoE models.
☆311Jun 24, 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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆117Dec 15, 2025Updated 6 months ago
- ☆13Jun 29, 2024Updated 2 years ago
- Compiler for Dynamic Neural Networks☆45Nov 13, 2023Updated 2 years ago
- Curated collection of papers in MoE model inference☆400Mar 12, 2026Updated 3 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆222Sep 21, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A low-latency & high-throughput serving engine for LLMs☆507Jan 8, 2026Updated 5 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆267Nov 18, 2024Updated last year
- ☆321Jul 10, 2025Updated 11 months ago
- ☆62May 4, 2024Updated 2 years ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆397Jul 10, 2025Updated 11 months ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆16May 6, 2024Updated 2 years ago
- ☆134Nov 11, 2024Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆498Jun 10, 2026Updated 2 weeks ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆329Jun 10, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Code release for AdapMoE accepted by ICCAD 2024☆39Apr 28, 2025Updated last year
- ☆20Sep 28, 2024Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,332Aug 28, 2025Updated 10 months ago
- ☆91Oct 17, 2025Updated 8 months ago
- ☆48Jun 27, 2024Updated 2 years ago
- STREAMer: Benchmarking remote volatile and non-volatile memory bandwidth☆18Aug 21, 2023Updated 2 years ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆533Updated this week
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆98Jun 16, 2025Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆54Aug 6, 2025Updated 10 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆539Feb 10, 2025Updated last year
- Serverless LLM Serving for Everyone.☆686May 4, 2026Updated last month
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆151Dec 4, 2024Updated last year
- A GPU-driven system framework for scalable AI applications☆132Updated this week
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,890Updated this week
- ☆257Oct 24, 2025Updated 8 months ago
- ☆48Dec 19, 2025Updated 6 months ago
- Stateful LLM Serving☆103Mar 11, 2025Updated last year
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆56Aug 6, 2025Updated 10 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A throughput-oriented high-performance serving framework for LLMs☆962Mar 29, 2026Updated 3 months ago
- ☆159Oct 9, 2024Updated last year
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆96May 14, 2026Updated last month
- Efficient and easy multi-instance LLM serving☆555Mar 12, 2026Updated 3 months ago
- LLM Serving Performance Evaluation Harness☆84Feb 25, 2025Updated last year
- An interference-aware scheduler for fine-grained GPU sharing☆163Nov 26, 2025Updated 7 months ago
- A sparse attention kernel supporting mix sparse patterns☆528Jan 18, 2026Updated 5 months ago