woct0rdho / transformers-qwen3-moe-fusedLinks
Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth
☆156Updated this 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:
- A collection of tricks and tools to speed up transformer models☆169Updated 2 months ago
- A repository aimed at pruning DeepSeek V3, R1 and R1-zero to a usable size☆65Updated 4 months ago
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆173Updated 3 weeks ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆83Updated 3 months ago
- ☆290Updated 2 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 3 months ago
- Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆96Updated 3 weeks ago
- ☆55Updated 3 months ago
- Auto Thinking Mode switch for Qwen3 in Open webui☆67Updated 3 months ago
- ☆51Updated last year
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆186Updated 2 months ago
- Deep Reasoning Translation (DRT) Project☆227Updated 2 months ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆136Updated last year
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆220Updated last month
- ☆144Updated 9 months ago
- The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆92Updated last month
- ☆61Updated 5 months ago
- ☆92Updated 2 weeks ago
- ☆102Updated 11 months ago
- ☆90Updated 3 months ago
- Implemented a script that automatically adjusts Qwen3's inference and non-inference capabilities, based on an OpenAI-like API. The infere…☆22Updated 3 months ago
- ☆78Updated 4 months ago
- XVERSE-MoE-A36B: A multilingual large language model developed by XVERSE Technology Inc.☆39Updated 11 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆90Updated 3 months ago
- CursorCore: Assist Programming through Aligning Anything☆131Updated 6 months ago
- RWKV-7: Surpassing GPT☆94Updated 9 months ago
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆293Updated 3 months ago
- Repo of ACL 2025 Paper "Quantification of Large Language Model Distillation"☆90Updated 3 weeks ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆429Updated 3 months ago
- GLM Series Edge Models☆147Updated 2 months ago