A repository aimed at pruning DeepSeek V3, R1 and R1-zero to a usable size
☆89Sep 5, 2025Updated last year
Alternatives and similar repositories for moe-pruner
Users that are interested in moe-pruner are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆93Oct 2, 2026Updated last month
- [TMLR] Official PyTorch implementation of CD-MOE☆12Mar 18, 2026Updated 8 months ago
- ☆12Dec 21, 2024Updated last year
- Direct Preference Optimization for RWKV, aiming for RWKV-5 and 6.☆11Mar 1, 2024Updated 2 years ago
- A 20M RWKV v6 can do nonogram☆13Oct 18, 2024Updated 2 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.
- ☆11Jul 10, 2026Updated 4 months ago
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆89Mar 25, 2025Updated last year
- ☆17Jan 1, 2025Updated last year
- [ICML25] Agentic Compression Benchmark (ACBench)☆22Jul 2, 2025Updated last year
- PyTorch implementation of the paper: Decomposing Vision Transformers for Collaborative Inference in Edge Devices☆18Jul 27, 2024Updated 2 years ago
- Code to reproduce the experiments of the ICLR24-paper: "Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging"☆12Oct 14, 2025Updated last year
- ☆41Apr 30, 2025Updated last year
- [ICLR 2025, IEEE TPAMI 2026] Mixture Compressor & MC#☆79Feb 12, 2025Updated last year
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆37Oct 9, 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.
- Sentence Splitting Dataset☆10Nov 5, 2019Updated 7 years ago
- An industrial extension library of pytorch to accelerate large scale model training☆62Oct 16, 2026Updated last month
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆265Jun 15, 2025Updated last year
- continous batching and parallel acceleration for RWKV6☆23Jun 28, 2024Updated 2 years ago
- Mini Model Daemon☆13Nov 9, 2024Updated 2 years ago
- This project is to extend RWKV LM's capabilities including sequence classification/embedding/peft/cross encoder/bi encoder/multi modaliti…☆10Aug 7, 2024Updated 2 years ago
- Mixture-of-Basis-Experts for Compressing MoE-based LLMs☆41Updated this week
- Code for "Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs"☆19Nov 6, 2025Updated last year
- Fused Qwen3 MoE layer for faster training, compatible with Transformers, LoRA, bnb 4-bit quant, Unsloth. Also possible to train LoRA over…☆262Jul 24, 2026Updated 3 months ago
- 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.
- Inference RWKV v7 in pure C.☆47Oct 10, 2025Updated last year
- Telegram bot which can work with both openAI and LocalAI modes, it also uses UncensoredGPT models like Wizard-Uncensored. It can be launc…☆21Mar 14, 2025Updated last year
- ☆17Nov 23, 2023Updated 2 years ago
- [ICCV 2025] TruthPrInt: Mitigating LVLM Object Hallucination Via Latent Truthful-Guided Pre-Intervention☆14Feb 11, 2026Updated 9 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆19Jul 20, 2023Updated 3 years ago
- [ICML 2025] Retraining-Free Merging of Sparse MoE via Hierarchical Clustering☆24Oct 26, 2025Updated last year
- Official Chinese documentation for RWKV | RWKV官方中文文档☆15Nov 2, 2026Updated 2 weeks ago
- ☆32May 26, 2024Updated 2 years ago
- In this project, I created prediction model for predict bitcoin price with Gated Recurrent Unit Model. GRU is a gating mechanism in recur…☆13Dec 10, 2020Updated 5 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Samples and demos with LangGraph and LangChain frameworks.☆16Aug 22, 2025Updated last year
- Lottery Ticket Adaptation☆40Nov 20, 2024Updated 2 years ago
- https://x.com/BlinkDL_AI/status/1884768989743882276☆29May 4, 2025Updated last year
- ☆13Feb 24, 2021Updated 5 years ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆102Sep 4, 2024Updated 2 years ago
- HFODetector is Python package that that is capable of detecting HFOs with STE / MNI / Hilbert detector. Detection speed is increased by u…☆13Feb 16, 2025Updated last year
- LLM serving simulator that uses DoolyProf's latency database; built around the vLLM's native scheduler.☆15Oct 28, 2026Updated 3 weeks ago
Are these results useful?