pdh930105

pdh930105's Stars

• ImagineAILab/ai-by-hand-excel

  2.4k655353

• hemingkx/SpeculativeDecodingPapers

  📰 Must-read papers and blogs on Speculative Decoding ⚡️

  56428426

• Haiyang-W/GiT

  [ECCV2024 Oral🔥] Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"

  Language:Python32371415

• gstoica27/ZipIt

  A framework for merging models solving different tasks with different initializations into one multi-task model without any additional training

  Language:Python29132725

• trevorpogue/algebraic-nnhw

  Algebraic enhancements for deep learning accelerator architectures

  Language:Python2645015

• feizc/DiT-MoE

  Scaling Diffusion Transformers with Mixture of Experts

  Language:Python2436811

• jxiw/MambaInLlama

  [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models

  Language:Python18962414

• CASE-Lab-UMD/LLM-Drop

  The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".

  Language:Python15841317

• ShoufaChen/Awesome-Diffusion-Transformers

  https://www.shoufachen.com/Awesome-Diffusion-Transformers/

  Language:HTML126618

• ChenMnZ/PrefixQuant

  An algorithm for static activation quantization of LLMs

  Language:Python1098235

• thunlp/Ouroboros

  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)

  Language:Python85769

• ChangyuanWang17/QVLM

  [NeurIPS'24]Efficient and accurate memory saving method towards W4A4 large multi-modal models.

  Language:Python58294

• NVlabs/COAT

  Language:Python52701

• smart-lty/ParallelSpeculativeDecoding

  The official code for paper "parallel speculative decoding with adaptive draft length."

  Language:Python31111

• Zhaoshixin-sky/CIM-MLC

  [ASPLOS 2024] CIM-MLC: A Multi-level Compilation Stack for Computing-In-Memory Accelerators

  Language:Python25224

• Intelligent-Computing-Lab-Yale/TesseraQ

  Language:Python18122

• PiggyJerry/DC-Net

  The code for paper: "DC-Net: Divide-and-Conquer for Salient Object Detection"

  Language:Python17251

• thunlp/Seq1F1B

  Sequence-level 1F1B schedule for LLMs.

  Language:Python16011

• ebby-s/MX-for-FPGA

  Implementation of Microscaling data formats in SystemVerilog.

  Language:SystemVerilog13202

• snu-comparch/Tender

  Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization (ISCA'24)

  Language:Python12301

• BidyutSaha/TinyTNAS

  TinyTNAS is a hardware-aware, multi-objective, time-bound Neural Architecture Search (NAS) tool designed for TinyML time series classification. Unlike GPU-based NAS methods, it runs efficiently on CPUs.

  Language:Python11200

• Cheliosoops/BitQ

  Language:Python11200

• abdelfattah-lab/shadow_llm

  Language:Python7311

• lynn2089/SmartLite

  Language:Python7122

• b-faye/OneEncoder

  Language:Python60

• ershang2/SlowTrack

  Language:Python5113

• pingxue-hfut/DWR

  Fast and Accurate Binary Neural Networks based on Depth-Width Reshaping

  Language:Python520

• yamilvindas/gdec

  Language:Python211

• dongwonjo/BinaryMoS

  Language:Python110

• naufalso/adversarial-manhole

  Official code for "Adversarial Manholes: Challenging Monocular Depth Estimation and Semantic Segmentation with Physical Attacks"

  Language:Python1201