Emericen / tiny-qwenLinks
A minimal PyTorch re-implementation of Qwen3 VL with a fancy CLI
☆316Updated this week
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☆194Updated last month
- ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory [COLM2025]☆200Updated 6 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆204Updated 2 months ago
- Fused Qwen3 MoE layer for faster training, compatible with Transformers, LoRA, bnb 4-bit quant, Unsloth. Also possible to train LoRA over…☆231Updated last week
- Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.☆314Updated this week
- Block Diffusion for Ultra-Fast Speculative Decoding☆533Updated this week
- A reproduction of the Deepseek-OCR model including training☆209Updated 2 months ago
- mllm-npu: training multimodal large language models on Ascend NPUs☆95Updated last year
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆226Updated 3 weeks ago
- Speed Always Wins: A Survey on Efficient Architectures for Large Language Models☆394Updated 3 months ago
- ☆449Updated 6 months ago
- Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation☆422Updated this week
- A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…☆101Updated 5 months ago
- 青稞Talk☆190Updated 3 weeks ago
- DeepSeek Native Sparse Attention pytorch implementation☆115Updated last month
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆469Updated 8 months ago
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆331Updated 8 months ago
- Fast and memory-efficient exact kmeans☆138Updated last week
- ☆230Updated last month
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆147Updated 10 months ago
- GLM Series Edge Models☆158Updated 8 months ago
- [ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.☆484Updated 2 months ago
- Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference☆241Updated last week
- A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.☆249Updated 9 months ago
- The official repository of the dots.vlm1 instruct models proposed by rednote-hilab.☆284Updated 4 months ago
- Implementation of FlashAttention in PyTorch☆180Updated last year
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆121Updated 8 months ago
- Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".☆283Updated 11 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆228Updated 3 months ago
- ☆74Updated 8 months ago