Emericen / tiny-qwenLinks
A minimal, easy-to-read PyTorch reimplementation of the Qwen3 and Qwen2.5 VL with a fancy CLI
☆146Updated 3 weeks ago
Alternatives and similar repositories for tiny-qwen
Users that are interested in tiny-qwen are comparing it to the libraries listed below
Sorting:
- A collection of tricks and tools to speed up transformer models☆180Updated last week
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆194Updated last week
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆192Updated 3 months ago
- ☆425Updated last month
- Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.☆130Updated last week
- Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth☆176Updated last week
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆68Updated last month
- mllm-npu: training multimodal large language models on Ascend NPUs☆92Updated last year
- 青稞Talk☆146Updated this week
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆443Updated 4 months ago
- Implementation of FlashAttention in PyTorch☆168Updated 8 months ago
- ☆57Updated 4 months ago
- Efficient LLM Inference over Long Sequences☆391Updated 3 months ago
- Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang☆56Updated 10 months ago
- Triton Documentation in Chinese Simplified / Triton 中文文档☆82Updated 5 months ago
- TransMLA: Multi-Head Latent Attention Is All You Need (NeurIPS 2025 Spotlight)☆365Updated 3 weeks ago
- GLM Series Edge Models☆149Updated 3 months ago
- ☆49Updated last week
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆328Updated 7 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆194Updated 3 months ago
- ☆78Updated 9 months ago
- ☆97Updated 4 months ago
- ☆82Updated 5 months ago
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆302Updated 4 months ago
- KV cache compression for high-throughput LLM inference☆138Updated 7 months ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆214Updated this week
- ☆107Updated last month
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 4 months ago
- ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory☆184Updated 2 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆231Updated 2 months ago