woct0rdho / transformers-qwen3-moe-fusedLinks
Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth
☆179Updated last week
Alternatives and similar repositories for transformers-qwen3-moe-fused
Users that are interested in transformers-qwen3-moe-fused are comparing it to the libraries listed below
Sorting:
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 4 months ago
- A repository aimed at pruning DeepSeek V3, R1 and R1-zero to a usable size☆69Updated 3 weeks ago
- ☆293Updated 4 months ago
- ☆91Updated 4 months ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆137Updated last year
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆192Updated 3 months ago
- ☆58Updated 4 months ago
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆197Updated last week
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆89Updated 4 months ago
- Nano repo for RL training of LLMs☆65Updated last month
- ☆97Updated last month
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆217Updated 2 months ago
- ☆84Updated 5 months ago
- A collection of tricks and tools to speed up transformer models☆181Updated 2 weeks ago
- FuseAI Project☆87Updated 8 months ago
- A pipeline for LLM knowledge distillation☆109Updated 5 months ago
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆41Updated last year
- Repo of ACL 2025 Paper "Quantification of Large Language Model Distillation"☆93Updated 2 months ago
- ☆51Updated last year
- [NeurIP'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆108Updated last week
- ☆71Updated 4 months ago
- patches for huggingface transformers to save memory☆29Updated 4 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆197Updated 4 months ago
- Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.☆134Updated this week
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆220Updated 2 weeks ago
- DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL☆159Updated 2 weeks ago
- Deep Reasoning Translation (DRT) Project☆233Updated last month
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆99Updated last month
- Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?☆116Updated 11 months ago
- Efficient Agent Training for Computer Use☆132Updated 3 weeks ago