Explore Inter-layer Expert Affinity in MoE Model Inference
☆16May 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:
- Code Repository for the NeurIPS 2024 Paper "Toward Efficient Inference for Mixture of Experts".☆19Oct 30, 2024Updated last year
- Code release for AdapMoE accepted by ICCAD 2024☆38Apr 28, 2025Updated last year
- ☆61May 4, 2024Updated 2 years ago
- ☆29May 24, 2024Updated 2 years ago
- ATC23 AE☆45May 11, 2023Updated 3 years 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.
- Battleship environment for reinforcement learning tasks☆14Apr 29, 2023Updated 3 years ago
- KDSS is the framework for knowledge distillation from LLMs☆12Nov 5, 2025Updated 7 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆266Nov 18, 2024Updated last year
- [ICLR 2025] DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models☆19Mar 25, 2025Updated last year
- ☆21Feb 10, 2025Updated last year
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs☆25Nov 11, 2025Updated 6 months ago
- Inference framework for MoE layers based on TensorRT with Python binding☆41May 31, 2021Updated 5 years ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆43Aug 14, 2024Updated last year
- High-performance GEMM implementation optimized for NVIDIA H100 GPUs, leveraging Hopper architecture's TMA, WGMMA, and Thread Block Cluste…☆11Dec 4, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆308May 4, 2026Updated last month
- ASIC simulation of Multi-ported Memory Module. And it can offer SRAM-based dual-port basic building block to support multiple read/write …☆23May 30, 2016Updated 10 years ago
- Tutorial Exercises and Code for GPU Communications Tutorial at HOT Interconnects 2025☆32Oct 22, 2025Updated 7 months ago
- ☆15Apr 11, 2024Updated 2 years ago
- MISO: Exploiting Multi-Instance GPU Capability on Multi-Tenant GPU Clusters☆21Apr 21, 2023Updated 3 years ago
- ☆318Jul 10, 2025Updated 10 months ago
- ☆92Apr 2, 2022Updated 4 years ago
- Curated collection of papers in MoE model inference☆397Mar 12, 2026Updated 2 months ago
- [NSDI25] AutoCCL: Automated Collective Communication Tuning for Accelerating Distributed and Parallel DNN Training☆32May 2, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Pure Java Llama2 inference with optional multi-GPU CUDA implementation☆13Sep 2, 2023Updated 2 years ago
- Code for MLSys 2024 Paper "SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models"☆22Apr 13, 2024Updated 2 years ago
- The code based on vLLM for the paper “ Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention”.☆11Sep 19, 2024Updated last year
- Compiler for Dynamic Neural Networks☆45Nov 13, 2023Updated 2 years ago
- STREAMer: Benchmarking remote volatile and non-volatile memory bandwidth☆18Aug 21, 2023Updated 2 years ago
- JAX Scalify: end-to-end scaled arithmetics☆18Oct 30, 2024Updated last year
- An experimentation platform for LLM inference optimisation☆36Sep 19, 2024Updated last year
- linux 内核技术文档☆16Apr 27, 2026Updated last month
- Visualize expert firing frequencies across sentences in the Mixtral MoE model☆18Dec 22, 2023Updated 2 years ago
- 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.
- ☆21Jun 9, 2025Updated last year
- ☆18Apr 15, 2025Updated last year
- The pmem.io Website☆17Jan 20, 2026Updated 4 months ago
- This module collects per-page stats and decide for each page if it should be migrated, replicated or interleaved.☆17Sep 29, 2015Updated 10 years ago
- Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training☆24Mar 1, 2024Updated 2 years ago
- [ICLR 2025] Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better☆16Feb 15, 2025Updated last year
- Codes of the paper Deformable Butterfly: A Highly Structured and Sparse Linear Transform.☆16Nov 1, 2021Updated 4 years ago