Alternatives and similar repositories for NasRec

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

• TencentARC / BEBR
  Official code for "Binary embedding based retrieval at Tencent"
  ☆44Updated last year
• NVlabs / EfficientDL
  ☆34Updated 7 months ago
• MILVLG / mlc-imp
  Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
  ☆13Updated last year
• facebookresearch / adaptive_scheduling
  Experimental scripts for researching data adaptive learning rate scheduling.
  ☆22Updated 2 years ago
• huggingface / pixparse
  Pixel Parsing. A reproduction of OCR-free end-to-end document understanding models with open data
  ☆23Updated last year
• facebookresearch / active_indexing
  Official implementation of "Active Image Indexing"
  ☆60Updated 2 years ago
• onnx / neural-compressor
  Model compression for ONNX
  ☆98Updated last year
• quic / efficient-transformers
  This library empowers users to seamlessly port pretrained models and checkpoints on the HuggingFace (HF) hub (developed using HF transfor…
  ☆85Updated this week
• lucidrains / light-recurrent-unit-pytorch
  Implementation of a Light Recurrent Unit in Pytorch
  ☆49Updated last year
• facebookresearch / multi_view_active_learning
  Code for paper Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Training
  ☆22Updated 2 years ago
• lucidrains / rela-transformer
  Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012
  ☆49Updated 3 years ago
• alenic / timm-models-explorer
  Timm model explorer
  ☆42Updated last year
• triton-inference-server / pytorch_backend
  The Triton backend for the PyTorch TorchScript models.
  ☆173Updated this week
• kyegomez / Blockwise-Parallel-Transformer
  32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.
  ☆50Updated 2 years ago
• snu-mllab / LayerMerge
  Official PyTorch implementation of "LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging" (ICML 2024)
  ☆31Updated last year
• OpenNLPLab / LASP
  Linear Attention Sequence Parallelism (LASP)
  ☆88Updated last year
• yuzhenmao / IceFormer
  Implementation of IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs (ICLR 2024).
  ☆25Updated 6 months ago
• RobertCsordas / moe_attention
  Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"
  ☆102Updated last year
• lucidrains / self-reasoning-tokens-pytorch
  Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto
  ☆57Updated last year
• meta-pytorch / superblock
  A block oriented training approach for inference time optimization.
  ☆34Updated last year
• tridao / flash-attention-wheels
  ☆61Updated 2 years ago
• etienne87 / pytorch-stream-dataloader
  ☆52Updated 3 years ago
• facebookresearch / coocmap
  code for paper "Accessing higher dimensions for unsupervised word translation"
  ☆22Updated 2 years ago
• facebookresearch / PostText
  PostText is a QA system for querying your text data. When appropriate structured views are in place, PostText is good at answering querie…
  ☆31Updated 2 years ago
• IST-DASLab / SparseFinetuning
  Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry
  ☆42Updated 2 years ago
• kyegomez / Infini-attention
  Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTO…
  ☆58Updated last week
• crypdick / timm-lr-scheduler-explorer
  A dashboard for exploring timm learning rate schedulers
  ☆19Updated last year
• triton-inference-server / onnxruntime_backend
  The Triton backend for the ONNX Runtime.
  ☆172Updated last week
• lucidrains / mixture-of-attention
  Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts
  ☆122Updated last year
• PINTO0309 / sne4onnx
  A very simple tool for situations where optimization with onnx-simplifier would exceed the Protocol Buffers upper file size limit of 2GB,…
  ☆17Updated this week