Explore Inter-layer Expert Affinity in MoE Model Inference
☆17May 6, 2024Updated 2 years ago
Alternatives and similar repositories for ExFlow
Users that are interested in ExFlow are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆11Feb 7, 2025Updated last year
- Code Repository for the NeurIPS 2024 Paper "Toward Efficient Inference for Mixture of Experts".☆19Oct 30, 2024Updated last year
- FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving☆12Aug 3, 2026Updated 2 months ago
- [NeurIPS2024] "Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design", Ruisi Cai, Yeonju Ro, Geon-Woo …☆16Dec 16, 2024Updated last year
- ☆92Apr 2, 2022Updated 4 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆13Jun 29, 2024Updated 2 years ago
- Code release for AdapMoE accepted by ICCAD 2024☆40Apr 28, 2025Updated last year
- Code for MLSys 2024 Paper "SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models"☆23Apr 13, 2024Updated 2 years ago
- ☆16Jan 14, 2025Updated last year
- ☆64May 4, 2024Updated 2 years ago
- ATC23 AE☆45May 11, 2023Updated 3 years ago
- ☆29May 24, 2024Updated 2 years ago
- KDSS is the framework for knowledge distillation from LLMs☆12Nov 5, 2025Updated 11 months ago
- Official code for the paper "HEXA-MoE: Efficient and Heterogeneous-Aware MoE Acceleration with Zero Computation Redundancy"☆16Mar 6, 2025Updated last year
- 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.
- LM/VLM implementations☆12Oct 13, 2026Updated 2 weeks ago
- Battleship environment for reinforcement learning tasks☆15Apr 29, 2023Updated 3 years ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆267Nov 18, 2024Updated last year
- Inline PTX Assembly in CUDA example☆15Oct 5, 2026Updated 3 weeks ago
- Inference framework for MoE layers based on TensorRT with Python binding☆40May 31, 2021Updated 5 years ago
- Velocity Kernel for the Samsung Galaxy S8/S8+ (dreamlte/dream2lte). (discontinued)☆10May 30, 2019Updated 7 years ago
- ☆22Feb 10, 2025Updated last year
- ☆12Dec 17, 2022Updated 3 years ago
- High-performance GEMM implementation optimized for NVIDIA H100 GPUs, leveraging Hopper architecture's TMA, WGMMA, and Thread Block Cluste…☆11Aug 25, 2026Updated 2 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- 简单的大冲锋登录系统，包含自建的本地服务端，可实现单人模式一键进图，目前极为简陋仅供测试，后 续可能(不会)进一步开发。☆24Jul 25, 2026Updated 3 months ago
- ☆14Dec 22, 2024Updated last year
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆44Aug 14, 2024Updated 2 years ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆376Updated this week
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆53Aug 2, 2026Updated 2 months ago
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs☆25Nov 11, 2025Updated 11 months ago
- MISO: Exploiting Multi-Instance GPU Capability on Multi-Tenant GPU Clusters☆21Apr 21, 2023Updated 3 years ago
- CUDA MoE kernels.☆12Sep 21, 2024Updated 2 years ago
- This repo contains the implementation of deep reinforcement learning (DRL) algorithms for virtual machine rescheduling in data centers.☆12Dec 2, 2022Updated 3 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆13Aug 28, 2026Updated 2 months ago
- ☆15Apr 11, 2024Updated 2 years ago
- ASIC simulation of Multi-ported Memory Module. And it can offer SRAM-based dual-port basic building block to support multiple read/write …☆25May 30, 2016Updated 10 years ago
- Serve large files on Cloudflare Pages directly from Git LFS☆16Sep 1, 2023Updated 3 years ago
- Compiler for Dynamic Neural Networks☆45Nov 13, 2023Updated 2 years ago
- Intrinsic Curiosity Module (ICM) + PPO on the Pyramid and PushBlock environment.☆12Sep 3, 2019Updated 7 years ago
- An experimentation platform for LLM inference optimisation☆36Sep 19, 2024Updated 2 years ago