Alternatives and similar repositories for atorch

Users that are interested in atorch are comparing it to the libraries listed below

• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆241Updated 2 months ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆281Updated last year
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆144Updated last month
• Gaffey / ExCP
  Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".
  ☆48Updated last year
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆362Updated this week
• sgl-project / SpecForge
  Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
  ☆428Updated this week
• madsys-dev / deepseekv2-profile
  ☆148Updated 7 months ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆154Updated last week
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆78Updated last year
• AniZpZ / AutoSmoothQuant
  An easy-to-use package for implementing SmoothQuant for LLMs
  ☆107Updated 6 months ago
• NVIDIA-NeMo / Megatron-Bridge
  Training library for Megatron-based models
  ☆125Updated this week
• InternLM / turbomind
  ☆96Updated 6 months ago
• OpenPPL / ppl.llm.serving
  ☆129Updated 9 months ago
• qingkelab / qingketalk
  青稞Talk
  ☆151Updated this week
• Victarry / PP-Schedule-Visualization
  Pipeline Parallelism Emulation and Visualization
  ☆67Updated 4 months ago
• xlite-dev / ffpa-attn
  🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
  ☆223Updated 2 months ago
• MayDomine / Burst-Attention
  Distributed IO-aware Attention algorithm
  ☆21Updated 3 weeks ago
• RulinShao / LightSeq
  Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training
  ☆216Updated last year
• FlagOpen / FlagCX
  ☆91Updated this week
• ByteDance-Seed / cudaLLM
  ☆120Updated 2 months ago
• rlite-project / RLite
  A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…
  ☆68Updated last month
• feifeibear / long-context-attention
  USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
  ☆576Updated this week
• sail-sg / zero-bubble-pipeline-parallelism
  Zero Bubble Pipeline Parallelism
  ☆432Updated 5 months ago
• ByteDance-Seed / ByteCheckpoint
  ByteCheckpoint: An Unified Checkpointing Library for LFMs
  ☆249Updated 3 months ago
• RiseAI-Sys / DAX
  High performance inference engine for diffusion models
  ☆94Updated last month
• ByteDance-Seed / decoupleQ
  A quantization algorithm for LLM
  ☆143Updated last year
• microsoft / chunk-attention
  ☆78Updated 6 months ago
• ModelTC / EasyLLM
  Built upon Megatron-Deepspeed and HuggingFace Trainer, EasyLLM has reorganized the code logic with a focus on usability. While enhancing …
  ☆48Updated last year
• stepfun-ai / Step3
  ☆428Updated 2 months ago
• Dao-AILab / grouped-latent-attention
  ☆130Updated 4 months ago