[CVPR 2026] This is the official PyTorch implementation of "MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping".
☆34Mar 16, 2026Updated 8 months ago
Alternatives and similar repositories for MoDES
Users that are interested in MoDES are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2026] This is the official PyTorch implementation of "QVGen: Pushing the Limit of Quantized Video Generative Models".☆34Feb 11, 2026Updated 9 months ago
- [ICML 2025] Retraining-Free Merging of Sparse MoE via Hierarchical Clustering☆24Oct 26, 2025Updated last year
- ☆14Aug 31, 2026Updated 2 months ago
- Post-Trained MoE Can Skip Half Experts via Self-Distillation☆42Sep 6, 2026Updated 2 months ago
- [CVPR2025] FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression☆61Oct 10, 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.
- [ACL'25 Main] Official Implementation of HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Languag…☆57Jun 1, 2026Updated 5 months ago
- Official implementation of ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models☆24Jun 19, 2026Updated 5 months ago
- [arXiv 2026] This is the official PyTorch implementation of "RTDMD: Reinforcing Few-step Generators via Reward-Tilted Distribution Matchi…☆50Jun 6, 2026Updated 5 months ago
- BGEMM-CUDA is a CUDA-based low-bit GEMM kernel library for efficient neural network inference. It implements optimized binary and ternary…☆21Aug 30, 2024Updated 2 years ago
- A tool for model sparse based on torch.fx☆13Jun 3, 2024Updated 2 years ago
- [ICCV 2025] This repo is the official implementation of "Music Grounding by Short Video"☆26Sep 9, 2025Updated last year
- Official PyTorch implementation of QwT—“Quantization without Tears” (CVPR 2025): fast, accurate, and hassle-free post-training network qu…☆35Sep 30, 2025Updated last year
- [ECCV2024] The code of "SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning"☆10Oct 15, 2024Updated 2 years ago
- Official implementation of "Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent".☆23May 23, 2025Updated last year
- 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.
- ☆11May 7, 2026Updated 6 months ago
- 🧂[Preprint] Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation☆25Nov 9, 2026Updated last week
- ☆18Apr 7, 2025Updated last year
- ☆12Dec 19, 2024Updated last year
- Pytorch Implementation of Reliable Thinking with Images.☆31May 3, 2026Updated 6 months ago
- CVPR 2026☆14Mar 6, 2026Updated 8 months ago
- Instruction Tuning in Continual Learning paradigm☆86Oct 5, 2026Updated last month
- [ICLR 2025] RaSA: Rank-Sharing Low-Rank Adaptation☆10May 19, 2025Updated last year
- The official implementation of the paper "Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts" (ICLR 2026).☆23Oct 2, 2026Updated last month
- 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.
- ☆26Updated this week
- [ICLR 2026] HILBERT-GUIDED SPARSE LOCAL ATTENTION☆11Feb 13, 2026Updated 9 months ago
- Official Pytorch Implementation of "Outlier-weighed Layerwise Sampling for LLM Fine-tuning" by Pengxiang Li, Lu Yin, Xiaowei Gao, Shiwei …☆35Jun 3, 2025Updated last year
- Vision-G1, a reasoning Vision-Language Model (VLM) from Reinforcement Learning☆12Aug 31, 2025Updated last year
- [ICLR 2026] Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation☆12Jan 27, 2026Updated 9 months ago
- ☆15Apr 11, 2026Updated 7 months ago
- ☆11Jul 14, 2020Updated 6 years ago
- ☆10Jan 14, 2025Updated last year
- Open source repo for simple SOTA method.☆14Apr 21, 2026Updated 6 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- This repo has the PyTorch implementation and datasets of our WSDM 2023 paper: “Multi-queue Momentum Contrast for Microvideo-Product Retri…☆10Sep 17, 2023Updated 3 years ago
- ☆11Jul 5, 2026Updated 4 months ago
- ♊ Minimal PyTorch Twin Delayed DDPG (TD3) implementation☆10Jun 20, 2021Updated 5 years ago
- ☆36Nov 18, 2025Updated last year
- ☆29Dec 2, 2024Updated last year
- Code for the paper "H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition" (NeurIPS 2025)☆11Oct 28, 2025Updated last year
- [NeurIPS 2026] DAWN: Dependency-Aware Fast Inference for Diffusion LLMs.☆13Nov 7, 2026Updated last week
Are these results useful?