jmluu / Awesome-Efficient-TrainingView external linksLinks
A collection of research papers on efficient training of DNNs
☆70Jul 6, 2022Updated 3 years ago
Alternatives and similar repositories for Awesome-Efficient-Training
Users that are interested in Awesome-Efficient-Training are comparing it to the libraries listed below
Sorting:
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Jun 6, 2024Updated last year
- Implementation of Hyena Hierarchy in JAX☆10Apr 30, 2023Updated 2 years ago
- ☆11Oct 11, 2023Updated 2 years ago
- ☆11Aug 2, 2024Updated last year
- ☆16Dec 19, 2024Updated last year
- Benchmark PyTorch Custom Operators☆14Jul 6, 2023Updated 2 years ago
- [ICLR 2021 Spotlight] "CPT: Efficient Deep Neural Network Training via Cyclic Precision" by Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yinin…☆31Mar 2, 2024Updated last year
- Implementation of "NITI: Training Integer Neural Networks Using Integer-only Arithmetic" on arxiv☆90Jul 26, 2022Updated 3 years ago
- ☆14Nov 7, 2025Updated 3 months ago
- Training with Block Minifloat number representation☆18May 2, 2021Updated 4 years ago
- ☆19Dec 4, 2025Updated 2 months ago
- Xmixers: A collection of SOTA efficient token/channel mixers☆28Sep 4, 2025Updated 5 months ago
- A novel FPGA-based intent recognition systemutilizing deep recurrent neural networks☆27Aug 25, 2021Updated 4 years ago
- Revisiting Parameter Sharing for Automatic Neural Channel Number Search, NeurIPS 2020☆22Nov 15, 2020Updated 5 years ago
- This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".☆121Dec 12, 2021Updated 4 years ago
- torch_quantizer is a out-of-box quantization tool for PyTorch models on CUDA backend, specially optimized for Diffusion Models.☆23Mar 29, 2024Updated last year
- ☆24Sep 25, 2024Updated last year
- Code needed to reproduce results from my ICLR 2019 paper on fixed-point quantization of the backprop algorithm.☆10Jan 24, 2019Updated 7 years ago
- ☆11Apr 3, 2023Updated 2 years ago
- APPy (Annotated Parallelism for Python) enables users to annotate loops and tensor expressions in Python with compiler directives akin to…☆30Jan 28, 2026Updated 2 weeks ago
- [ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Mod…☆31Mar 12, 2024Updated last year
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Apr 17, 2024Updated last year
- Low Precision Arithmetic Simulation in PyTorch☆292May 20, 2024Updated last year
- ICME2022 Special Session “Beyond Accuracy: Responsible, Responsive, and Robust Multimedia Retrieval ”☆12Jun 3, 2024Updated last year
- Generate an FPGA design for a TWN☆10Nov 4, 2019Updated 6 years ago
- ☆13Dec 15, 2025Updated 2 months ago
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆67Jul 8, 2025Updated 7 months ago
- The (open-source part of) code to reproduce "BPPSA: Scaling Back-propagation by Parallel Scan Algorithm".☆13Jun 7, 2021Updated 4 years ago
- Official code of "NAS acceleration via proxy data", IJCAI21☆10May 29, 2022Updated 3 years ago
- Paper list for accleration of transformers☆14Jul 1, 2023Updated 2 years ago
- Combining SOAP and MUON☆19Feb 11, 2025Updated last year
- Official Pytorch Implementation for the paper 'SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients'☆17Jan 12, 2022Updated 4 years ago
- HGRN2: Gated Linear RNNs with State Expansion☆56Aug 20, 2024Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆89Oct 22, 2024Updated last year
- Approximate layers - TensorFlow extension☆27Apr 14, 2025Updated 10 months ago
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32May 25, 2024Updated last year
- ☆53May 20, 2024Updated last year
- Simple implementation of a GPT (training and inference) in PyTorch.☆13Dec 11, 2023Updated 2 years ago
- ☆12May 22, 2022Updated 3 years ago