[ICLR 2026] SERE: Similarity-Based Expert Re-routing for Efficient Batch Decoding in MoE Models
☆21Feb 4, 2026Updated 7 months ago
Alternatives and similar repositories for SERE
Users that are interested in SERE are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML 2025] Retraining-Free Merging of Sparse MoE via Hierarchical Clustering☆25Oct 26, 2025Updated 10 months ago
- [OSDI 2025] DecDEC: A Systems Approach to Advancing Low‑Bit LLM Quantization☆27Sep 1, 2026Updated 2 weeks ago
- [NeurIPS 2025] Speculate Deep and Accurate☆25Aug 10, 2026Updated last month
- Unofficial implementation of "Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle"☆12Jul 3, 2024Updated 2 years ago
- MobileNetV2: Inverted Residuals and Linear Bottlenecks☆10Jul 22, 2019Updated 7 years ago
- 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.
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆86Mar 25, 2025Updated last year
- ☆16Jul 7, 2026Updated 2 months ago
- ☆44Jun 14, 2026Updated 3 months ago
- Code release for AdapMoE accepted by ICCAD 2024☆39Apr 28, 2025Updated last year
- ☆31Jul 28, 2026Updated last month
- Implementation for Revela: Dense Retriever Learning via Language Modeling - ICLR 2026 Oral☆24Mar 26, 2026Updated 5 months ago
- ☆15Jan 24, 2025Updated last year
- ☆13Apr 27, 2024Updated 2 years ago
- [SIGCOMM 2023] PacketGame: Multi-Stream Packet Gating for Concurrent Video Inference at Scale☆15Jul 1, 2023Updated 3 years ago
- 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.
- Code for paper "Rethinking Text-based Protein Understanding: Retrieval or LLM?"☆21Oct 7, 2025Updated 11 months ago
- ☆19Oct 11, 2025Updated 11 months ago
- The official implementation of the paper "Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts" (ICLR 2026).☆22Aug 22, 2026Updated 3 weeks ago
- ☆13Oct 13, 2025Updated 11 months ago
- ☆11Jun 27, 2021Updated 5 years ago
- Burstable Cloud Scheduler☆17Jun 6, 2024Updated 2 years ago
- Here is the official code for 《Nature Communications》 "Navigating Chemical-Linguistic Sharing Space with Heterogeneous Molecular Encoding…☆28May 23, 2026Updated 3 months ago
- ☆21May 12, 2026Updated 4 months ago
- Code Repository for the NeurIPS 2024 Paper "Toward Efficient Inference for Mixture of Experts".☆19Oct 30, 2024Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Plato is a system for viewport adaptation based bitrate adaptive VR video streaming.☆15May 1, 2018Updated 8 years ago
- Integrating Event-based Dynamic Vision Sensors with Sparse Hyperdimensional Computing☆13Jul 9, 2020Updated 6 years ago
- ☆31Feb 3, 2026Updated 7 months ago
- Layered prefill changes the scheduling axis from tokens to layers and removes redundant MoE weight reloads while keeping decode stall fre…☆20Mar 9, 2026Updated 6 months ago
- [ICLR 2026] AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Size☆16Jan 28, 2026Updated 7 months ago
- ☆26Sep 17, 2024Updated 2 years ago
- Low-Latency Live Video Streaming over a Low-Earth-Orbit Satellite Network with DASH☆18Sep 6, 2024Updated 2 years ago
- Lightning Training strategy for HiveMind☆18Jan 20, 2026Updated 7 months ago
- dUltra: Ultra-Fast Diffusion Large Language Models via Reinforcement Learning☆18Jul 11, 2026Updated 2 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- A flexible framework for AI agents that separates workflow logic from search strategy. Based on https://arxiv.org/pdf/2512.03571 Also rea…☆23Feb 10, 2026Updated 7 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
- Curated collection of papers in MoE model inference☆426Mar 12, 2026Updated 6 months ago
- Introduce a continuous intermediate representation between "masks" and "tokens" for dLLM☆15Dec 1, 2025Updated 9 months ago
- KAIST medical VL research group☆20Dec 20, 2024Updated last year
- Swiss-system tournament manager in python 3.☆11Aug 13, 2021Updated 5 years ago
- ☆13Apr 16, 2018Updated 8 years ago