dhcode-cpp / online-softmaxLinks
simplest online-softmax notebook for explain Flash Attention
☆13Updated 8 months ago
Alternatives and similar repositories for online-softmax
Users that are interested in online-softmax are comparing it to the libraries listed below
Sorting:
- Pipeline-Parallel Lecture: Simplest Dualpipe Implementation.☆27Updated 2 months ago
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆50Updated last year
- Implementation of FlashAttention in PyTorch☆162Updated 7 months ago
- qwen-nsa☆74Updated 4 months ago
- Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.☆89Updated this week
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆120Updated last year
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆67Updated 2 years ago
- Inference code for LLaMA models☆122Updated 2 years ago
- ☆143Updated last month
- ☆79Updated last year
- ☆52Updated 2 years ago
- Efficient Mixture of Experts for LLM Paper List☆118Updated this week
- An easy-to-use package for implementing SmoothQuant for LLMs☆105Updated 4 months ago
- simplify >2GB large onnx model☆63Updated 9 months ago
- from MHA, MQA, GQA to MLA by 苏剑林, with code☆28Updated 6 months ago
- ☆146Updated 5 months ago
- Transformer related optimization, including BERT, GPT☆59Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆108Updated 4 months ago
- Triton Documentation in Chinese Simplified / Triton 中文文档☆80Updated 4 months ago
- 青稞Talk☆135Updated this week
- export llama to onnx☆132Updated 8 months ago
- [ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"☆47Updated last year
- Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang☆56Updated 9 months ago
- ☆45Updated 2 months ago
- Models and examples built with OneFlow☆98Updated 10 months ago
- DeepSeek Native Sparse Attention pytorch implementation☆91Updated 3 weeks ago
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆58Updated last year
- 模型压缩的小白入门教程☆22Updated last year
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- ☆84Updated last year