dhcode-cpp / online-softmaxLinks
simplest online-softmax notebook for explain Flash Attention
☆13Updated 7 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.☆25Updated last month
- Implementation of FlashAttention in PyTorch☆159Updated 6 months ago
- from MHA, MQA, GQA to MLA by 苏剑林, with code☆25Updated 5 months ago
- ☆52Updated 2 years ago
- qwen-nsa☆70Updated 3 months ago
- ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化☆50Updated last year
- ☆140Updated last month
- Inference code for LLaMA models☆122Updated last year
- Models and examples built with OneFlow☆98Updated 9 months ago
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆66Updated 2 years ago
- ☆30Updated 5 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆102Updated 3 months ago
- ☆79Updated last year
- Transformer related optimization, including BERT, GPT☆17Updated 2 years ago
- Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.☆97Updated last year
- ☆145Updated 5 months ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆117Updated last year
- ☆83Updated last year
- llm theoretical performance analysis tools and support params, flops, memory and latency analysis.☆101Updated 3 weeks ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆103Updated 4 months ago
- Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library☆41Updated last week
- Triton Documentation in Chinese Simplified / Triton 中文文档☆78Updated 3 months ago
- DeepSpeed教程 & 示例注释 & 学习笔记 (大模型高效训练)☆173Updated last year
- an implementation of transformer, bert, gpt, and diffusion models for learning purposes☆155Updated 9 months ago
- ☆38Updated 2 years ago
- 模型压缩的小白入门教程☆22Updated last year
- DeepSeek Native Sparse Attention pytorch implementation☆83Updated 5 months ago
- Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.☆64Updated this week
- export llama to onnx☆131Updated 7 months ago
- 怎么训练一个LLM分词器☆151Updated 2 years ago