Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient
☆68Aug 3, 2025Updated last year
Alternatives and similar repositories for DenseMixer
Users that are interested in DenseMixer are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Implementation and datasets for "Training Language Models to Generate Quality Code with Program Analysis Feedback"☆43Jul 21, 2025Updated last year
- Source codes for paper "BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity".☆19Jan 10, 2026Updated 9 months ago
- ☆20Sep 6, 2025Updated last year
- The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".☆32Nov 12, 2024Updated last year
- BFloat16 Fused Adam Operator for PyTorch☆20Nov 16, 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.
- Sparse Backpropagation for Mixture-of-Expert Training☆30Jul 2, 2024Updated 2 years ago
- ☆23Jun 12, 2025Updated last year
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆307Nov 7, 2025Updated 11 months ago
- Code and training scripts for FlexOlmo☆155Apr 20, 2026Updated 5 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆232Nov 27, 2025Updated 10 months ago
- Code for Semi-crowdsourced Clustering with Deep Generative Models☆12Dec 9, 2022Updated 3 years ago
- Simple & Scalable Pretraining for Neural Architecture Research☆347Mar 31, 2026Updated 6 months ago
- ☆64Jul 10, 2025Updated last year
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆233Nov 4, 2025Updated 11 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- The official implementation of HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization☆19Mar 7, 2025Updated last year
- [EMNLP 2026] MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Scaling of Diffusion Language Models☆30Updated this week
- LM engine is a library for pretraining/finetuning LLMs☆196Sep 25, 2026Updated 2 weeks ago
- Training hybrid models for dummies.☆30Nov 1, 2025Updated 11 months ago
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆123Dec 20, 2024Updated last year
- [ICML2025] Official Repo for Paper "Optimizing Temperature for Language Models with Multi-Sample Inference"☆23Feb 16, 2025Updated last year
- Repository for paper: Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets☆31Apr 27, 2026Updated 5 months ago
- [Tech Report, NeurIPS 2026] Expanded Hyper-Connections☆69Sep 30, 2026Updated last week
- [COLM 2026] An efficient 3D sampling method for long-CoT LLM.☆16May 25, 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.
- Official github repo for "Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute"☆17Jun 30, 2025Updated last year
- ☆18Jun 2, 2026Updated 4 months ago
- Benchmarking Benchmark Leakage in Large Language Models☆61May 20, 2024Updated 2 years ago
- Post-Trained MoE Can Skip Half Experts via Self-Distillation☆42Sep 6, 2026Updated last month
- Official Implementation of Knowledge Flow Prompting☆35Oct 20, 2025Updated 11 months ago
- ☆125Feb 19, 2026Updated 7 months ago
- NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer☆49Mar 29, 2024Updated 2 years ago
- [NeurIPS 2024] OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI☆106Mar 6, 2025Updated last year
- Measuring the Signal to Noise Ratio in Language Model Evaluation☆32Aug 19, 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.
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆268Aug 9, 2025Updated last year
- A repo for open research on building large reasoning models☆154Jul 3, 2026Updated 3 months ago
- ☆25Aug 20, 2025Updated last year
- Transformer from Scratch in PyTorch☆18Mar 26, 2022Updated 4 years ago
- ☆147Feb 4, 2026Updated 8 months ago
- Code for 'Answer Matching Outperforms Multiple Choice for Language Model Evaluation' paper☆20Jul 4, 2025Updated last year
- Code for "What really matters in matrix-whitening optimizers?"☆25Oct 31, 2025Updated 11 months ago