Alternatives and similar repositories for online-softmax

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

• TRT2022 / trtllm-llama
  ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化
  ☆47Updated last year
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated last year
• zms1999 / SmartMoE
  A MoE impl for PyTorch, [ATC'23] SmartMoE
  ☆62Updated last year
• Ascend / AscendSpeed
  ☆79Updated last year
• cauyxy / bilivideos
  ☆52Updated last year
• luchangli03 / onnxsim_large_model
  simplify >2GB large onnx model
  ☆56Updated 5 months ago
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.
  ☆36Updated last month
• DD-DuDa / BitDistiller
  [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.
  ☆111Updated last year
• BBuf / megatron-lm-parallel-group-playground
  ☆16Updated last year
• void-main / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆59Updated last year
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆69Updated 11 months ago
• sunkx109 / llama
  Inference code for LLaMA models
  ☆120Updated last year
• shreyansh26 / FlashAttention-PyTorch
  Implementation of FlashAttention in PyTorch
  ☆146Updated 4 months ago
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆98Updated last month
• Adlik / smoothquantplus
  [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
  ☆23Updated last year
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆56Updated last year
• ironartisan / awesome-compression1
  模型压缩的小白入门教程
  ☆22Updated 10 months ago
• Tlntin / trt2023
  ☆24Updated last year
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆121Updated 4 months ago
• mdy666 / mdy_triton
  ☆125Updated 2 weeks ago
• preacher-1 / MLA_tutorial
  from MHA, MQA, GQA to MLA by 苏剑林, with code
  ☆18Updated 2 months ago
• AlibabaPAI / FLASHNN
  ☆94Updated 8 months ago
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆130Updated last year
• CoinCheung / gdGPT
  Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
  ☆95Updated last year
• caiwanxianhust / FasterLLaMA
  使用 CUDA C++ 实现的 llama 模型推理框架
  ☆56Updated 6 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆81Updated last month
• L1aoXingyu / llm-infer-bench
  ☆11Updated last year
• madsys-dev / deepseekv2-profile
  ☆132Updated 2 months ago
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• bojone / tiger
  A Tight-fisted Optimizer
  ☆47Updated 2 years ago