Alternatives and similar repositories for bf16_fused_adam

Users that are interested in bf16_fused_adam are comparing it to the libraries listed below

• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆48Updated last year
• kaiokendev / cutoff-len-is-context-len
  Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit
  ☆63Updated 2 years ago
• frankxwang / dpo-prefix-sharing
  DPO, but faster 🚀
  ☆43Updated 7 months ago
• ethansmith2000 / TransformerExperiments
  ☆19Updated 2 months ago
• recursal / GoldFinch-paper
  GoldFinch and other hybrid transformer components
  ☆46Updated 11 months ago
• fal-ai-community / nano-mdm
  Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun
  ☆55Updated 4 months ago
• fal-ai-community / NativeSparseAttention
  research impl of Native Sparse Attention (2502.11089)
  ☆54Updated 4 months ago
• sekstini / basedxl
  ☆18Updated last year
• kyleliang919 / Super_Muon
  ☆59Updated 3 months ago
• cloneofsimo / zeroshampoo
  ☆34Updated 10 months ago
• euclaise / supertrainer2000
  ☆49Updated last year
• test-time-training / ttt-tk
  ☆37Updated 3 months ago
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆44Updated 9 months ago
• NathanGodey / qfilters
  Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)
  ☆33Updated 4 months ago
• mgmalek / efficient_cross_entropy
  ☆112Updated last year
• RobertCsordas / moe
  Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"
  ☆38Updated last month
• kyegomez / Blockwise-Parallel-Transformer
  32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.
  ☆48Updated 2 years ago
• TRI-ML / linear_open_lm
  A repository for research on medium sized language models.
  ☆77Updated last year
• lucidrains / PEER-pytorch
  Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind
  ☆127Updated 10 months ago
• chu-tianxiang / QuIP-for-all
  QuIP quantization
  ☆54Updated last year
• lucidrains / transformer-lm-gan
  Explorations into adversarial losses on top of autoregressive loss for language modeling
  ☆37Updated 4 months ago
• cchan / nanoGPT-fp8
  ☆13Updated 2 years ago
• huyphan168 / PEER
  Mixture of A Million Experts
  ☆46Updated 11 months ago
• RWKV / ZeroCoT
  https://x.com/BlinkDL_AI/status/1884768989743882276
  ☆28Updated 2 months ago
• AnonymousAlethiometer / SGD_SaI
  Official PyTorch Implementation for Paper "No More Adam: Learning Rate Scaling at Initialization is All You Need"
  ☆52Updated 5 months ago
• BlinkDL / modded-nanogpt-rwkv
  RWKV-7: Surpassing GPT
  ☆92Updated 8 months ago
• joey00072 / ohara
  Collection of autoregressive model implementation
  ☆85Updated 2 months ago
• cloneofsimo / min-fsdp
  ☆80Updated last year
• Zyphra / Zyda_processing
  ☆36Updated last year
• fal-ai / diffusion-speedrun
  Focused on fast experimentation and simplicity
  ☆76Updated 6 months ago