Alternatives and similar repositories for Megatron-LM

Users that are interested in Megatron-LM are comparing it to the libraries listed below

• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆66Updated last year
• CalebDu / Awesome-Cute
  ☆108Updated 5 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆183Updated last month
• AlibabaPAI / FLASHNN
  ☆101Updated last year
• yifuwang / symm-mem-recipes
  ☆147Updated 10 months ago
• fzyzcjy / torch_memory_saver
  Allow torch tensor memory to be released and resumed later
  ☆164Updated last week
• microsoft / nnscaler
  nnScaler: Compiling DNN models for Parallel Training
  ☆118Updated last month
• KuangjuX / NVSHMEM-Tutorial
  NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer
  ☆142Updated last month
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆164Updated last month
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆140Updated 9 months ago
• weishengying / cutlass_flash_atten_fp8
  使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention
  ☆78Updated last year
• OpenPPL / ppl.llm.kernel.cuda
  ☆152Updated 10 months ago
• Victarry / PP-Schedule-Visualization
  Pipeline Parallelism Emulation and Visualization
  ☆70Updated 5 months ago
• thunlp / Seq1F1B
  Sequence-level 1F1B schedule for LLMs.
  ☆32Updated 2 months ago
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆114Updated 5 months ago
• madsys-dev / deepseekv2-profile
  ☆149Updated 8 months ago
• zhuohan123 / terapipe
  ☆77Updated 4 years ago
• ParCIS / Chimera
  Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.
  ☆67Updated 7 months ago
• ColfaxResearch / cfx-article-src
  ☆154Updated 6 months ago
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆247Updated 4 months ago
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆75Updated last week
• wu-kan / wuk_cupti_wrapper
  a simple API to use CUPTI
  ☆11Updated 2 months ago
• pzhao-eng / FlashMLA
  ☆59Updated 3 months ago
• InternLM / Awesome-LLM-Training-System
  ☆43Updated last year
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆96Updated 10 months ago
• flashinfer-ai / cutlass-viz
  ☆65Updated 6 months ago
• reed-lau / cute-gemm
  ☆138Updated 11 months ago
• LoongServe / LoongServe
  ☆124Updated last year
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• awslabs / optimizing-multitask-training-through-dynamic-pipelines
  Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines
  ☆20Updated last year