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
Alternatives and similar repositories for SiDA-MoE
Users that are interested in SiDA-MoE are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆13Oct 6, 2024Updated last year
- Battleship environment for reinforcement learning tasks☆14Apr 29, 2023Updated 3 years ago
- KDSS is the framework for knowledge distillation from LLMs☆12Nov 5, 2025Updated 9 months ago
- Code Repository for the NeurIPS 2024 Paper "Toward Efficient Inference for Mixture of Experts".☆19Oct 30, 2024Updated last year
- Official implementation of CrossPipe: Towards Optimal Pipeline Schedules for Cross-Datacenter Training (ATC '25), built on top of Megatro…☆17Jul 6, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Incremental Mobile User Profiling: Reinforcement Learning with Spatial Knowledge Graph for Modeling Event Streams☆15Jul 25, 2024Updated 2 years ago
- [AAAI 2026] Official implementation of "FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models". If you find this reposi…☆19Aug 26, 2026Updated last week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆352Updated this week
- Explore Inter-layer Expert Affinity in MoE Model Inference☆17May 6, 2024Updated 2 years ago
- Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism (NIPS'25)☆16Oct 6, 2025Updated 10 months ago
- ☆13Dec 9, 2024Updated last year
- ☆53Dec 26, 2024Updated last year
- Curated collection of papers in MoE model inference☆424Mar 12, 2026Updated 5 months ago
- Code for "Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes"☆32Mar 28, 2024Updated 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.
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆267Nov 18, 2024Updated last year
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆39Aug 29, 2025Updated last year
- 2022 USTC 011705 (OSH) Course Project of Runikraft Group☆13Jul 22, 2022Updated 4 years ago
- [ICML‘25] Official code for paper "Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training an…☆14Apr 17, 2025Updated last year
- STREAMer: Benchmarking remote volatile and non-volatile memory bandwidth☆18Aug 21, 2023Updated 3 years ago
- All-in-one benchmarking platform for evaluating LLM.☆15Nov 12, 2025Updated 9 months ago
- Towards Understanding the Mixture-of-Experts Layer in Deep Learning☆36Dec 12, 2023Updated 2 years ago
- ☆22May 27, 2025Updated last year
- Official implementation for the paper Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapp…☆15May 20, 2026Updated 3 months 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.
- ☆69Updated this week
- Storage Performance Development Kit☆12Updated this week
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆58Aug 21, 2024Updated 2 years ago
- deprecated, use https://github.com/octohelm/piper instead.☆14Sep 3, 2024Updated last year
- Optimizing data-intensive systems in disaggregated data centers☆13Jun 13, 2022Updated 4 years ago
- Debug print operator for cudagraph debugging☆18Aug 2, 2024Updated 2 years ago
- ☆32May 28, 2024Updated 2 years ago
- ☆85Feb 5, 2026Updated 6 months ago
- [ATC'25] Katz is a high-performance serving system designed specifically for diffusion model workflows with multiple adapters.☆24May 26, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- An LLM inference engine, written in C++☆20Mar 30, 2026Updated 5 months ago
- [ICML 2025] Efficiently Serving Large Multimodal Models Using EPD Disaggregation☆25Jul 11, 2026Updated last month
- Force google.com (aka Google No Country Redirect) when searching in Google Chrome Omnibox☆11Jul 7, 2026Updated last month
- Google 공식 Rouge Implementation을 한국어에서 사용할 수 있도록 처리☆17Jan 3, 2024Updated 2 years ago
- ☆27Nov 15, 2024Updated last year
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆69Dec 9, 2024Updated last year
- ☆14Nov 7, 2024Updated last year