Alternatives and similar repositories for online-softmax

Users that are interested in online-softmax are comparing it to the libraries listed below

• shreyansh26 / FlashAttention-PyTorch
  Implementation of FlashAttention in PyTorch
  ☆155Updated 6 months ago
• TRT2022 / trtllm-llama
  ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化
  ☆49Updated last year
• cauyxy / bilivideos
  ☆52Updated 2 years ago
• sunkx109 / llama
  Inference code for LLaMA models
  ☆122Updated last year
• mdy666 / mdy_triton
  ☆140Updated last week
• preacher-1 / MLA_tutorial
  from MHA, MQA, GQA to MLA by 苏剑林, with code
  ☆22Updated 4 months ago
• tingshua-yts / BetterDL
  ☆36Updated last year
• zms1999 / SmartMoE
  A MoE impl for PyTorch, [ATC'23] SmartMoE
  ☆64Updated 2 years ago
• CoinCheung / gdGPT
  Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
  ☆97Updated last year
• DD-DuDa / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆115Updated last year
• mdy666 / Qwen-Native-Sparse-Attention
  qwen-nsa
  ☆68Updated 3 months ago
• DD-DuDa / TensorRT-in-Action
  TensorRT-in-Action 是一个 GitHub 代码库，提供了使用 TensorRT 的代码示例，并有对应 Jupyter Notebook。
  ☆16Updated 2 years ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆102Updated 3 months ago
• Ascend / AscendSpeed
  ☆79Updated last year
• luchangli03 / export_llama_to_onnx
  export llama to onnx
  ☆129Updated 6 months ago
• firechecking / CleanTransformer
  an implementation of transformer, bert, gpt, and diffusion models for learning purposes
  ☆155Updated 9 months ago
• Tlntin / ChatGLM2-6B-TensorRT
  ☆90Updated 2 years ago
• void-main / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆59Updated last year
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated last year
• bobo0810 / LearnDeepSpeed
  DeepSpeed教程 & 示例注释 & 学习笔记 （大模型高效训练）
  ☆169Updated last year
• ironartisan / awesome-compression1
  模型压缩的小白入门教程
  ☆22Updated last year
• pp1230 / LLMGPUMemEstimator
  The GPU RAM Estimator provides a simple tool for estimating GPU memory usage during training and inference.
  ☆34Updated last year
• Oneflow-Inc / models
  Models and examples built with OneFlow
  ☆97Updated 9 months ago
• dhcode-cpp / NSA-pytorch
  DeepSeek Native Sparse Attention pytorch implementation
  ☆73Updated 4 months ago
• thuwyh / InferLight
  lightweighted deep learning inference service framework
  ☆39Updated 4 years ago
• Tlntin / qwen-ascend-llm
  ☆47Updated 8 months ago
• madsys-dev / deepseekv2-profile
  ☆145Updated 4 months ago
• SmartFlowAI / LLM101n-CN
  LLM101n: Let's build a Storyteller 中文版
  ☆131Updated 11 months ago
• yujunhuics / Reyes
  从零到一实现了一个多模态大模型，并命名为Reyes（睿视），R：睿，eyes：眼。Reyes的参数量为8B，视觉编码器使用的是InternViT-300M-448px-V2_5,语言模型侧使用的是Qwen2.5-7B-Instruct，Reyes也通过一个两层MLP投影层连…
  ☆22Updated 5 months ago
• yanqiangmiffy / how-to-train-tokenizer
  怎么训练一个LLM分词器
  ☆151Updated 2 years ago