#
Starred repositories
《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀
An implementation of the DISP-LLM method from the NeurIPS 2024 paper: Dimension-Independent Structural Pruning for Large Language Models.
Unofficial implementations of block/layer-wise pruning methods for LLMs.
For releasing code related to compression methods for transformers, accompanying our publications
FPGA-based hardware accelerator for Vision Transformer (ViT), with Hybrid-Grained Pipeline.
Spiking neural network implementation using Verilog with LIF (Leaky Integrate-and-Fire) neurons
Implementation of Adaptive Rank Selections for Low-Rank Approximation of Language Models
A curated list for Efficient Large Language Models
[NAACL 24 Oral] LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models
Tensor train based supervised machine learning estimator
Implementation of "NITI: Training Integer Neural Networks Using Integer-only Arithmetic" on arxiv
qianlima-lab / awesome-lifelong-learning-methods-for-llm
Forked from zzz47zzz/awesome-lifelong-learning-methods-for-llmThis repository collects awesome survey, resource, and paper for Lifelong Learning for Large Language Models. (Updated Regularly)
Awesome LLMs on Device: A Comprehensive Survey
IMAGine : An In-Memory Accelerated GEMV Engine Overlay
This is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as recommendation and natural language processing. We showed th…
A fully tensorized recurrent neural network using tensor-train decomposition
This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.
This is an official implementation for "Unified Low-rank Compression Framework for Click-through Rate Prediction".
Tensor decomposition for machine learning (w/ Python implementation)
TTM layer for forward and backward passes in language models
[ICCV 2023] I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference
Replace FC2, LeNet-5, VGG, Resnet, Densenet's full-connected layers with MPO