luliyucoordinate

luliyucoordinate's Stars

• microsoft/cusync

  Language:C++203

• microsoft/BitNet

  Official inference framework for 1-bit LLMs

  Language:C++12.4k873

• dimforge/wgmath

  GPU scientific computing on every platform

  Language:Rust413

• Shenyi-Z/ToCa

  Accelerating Diffusion Transformers with Token-wise Feature Caching

  Language:Python331

• ChenMnZ/PrefixQuant

  An algorithm for static activation quantization of LLMs

  Language:Python984

• mit-han-lab/duo-attention

  DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

  Language:Python40922

• kyutai-labs/moshi

  Language:Python7k549

• THU-DSP-LAB/ventus-gpgpu-verilog

  GPGPU supporting RISCV-V, developed with verilog HDL

  Language:Verilog7613

• kevmo314/scuda

  SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.

  Language:C++57921

• baidu-research/baidu-allreduce

  Language:Cuda571114

• thu-ml/SageAttention

  Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

  Language:Cuda71636

• tpn/pdfs

  Technically-oriented PDF Collection (Papers, Specs, Decks, Manuals, etc)

  Language:HTML7.8k1.5k

• gpgpu-sim/gpgpu-sim_distribution

  GPGPU-Sim provides a detailed simulation model of contemporary NVIDIA GPUs running CUDA and/or OpenCL workloads. It includes support for features such as TensorCores and CUDA Dynamic Parallelism as well as a performance visualization tool, AerialVisoin, and an integrated energy model, GPUWattch.

  Language:C++1.2k516

• THU-DSP-LAB/ventus-gpgpu

  GPGPU processor supporting RISCV-V extension, developed with Chisel HDL

  Language:Scala65477

• thuml/depyf

  depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.

  Language:Python52615

• GindaChen/FlexFlashAttention3

  FlexAttention w/ FlashAttention3 Support

  Language:Python272

• microsoft/VPTQ

  VPTQ, A Flexible and Extreme low-bit quantization algorithm

  Language:Python54636

• mobiusml/gemlite

  Fast low-bit matmul kernels in Triton

  Language:Python17713

• Tencent/TurboTransformers

  a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

  Language:C++1.5k198

• VivekPanyam/cudaparsers

  Parsers for CUDA binary files

  Language:Rust222

• Cornell-RelaxML/qtip

  Language:Python878

• chenzomi12/AISystem

  AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

  Language:Jupyter Notebook11.7k1.7k

• Huage001/LinFusion

  Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"

  Language:Python26717

• jbush001/NyuziProcessor

  GPGPU microprocessor architecture

  Language:C2k356

• gojasper/flash-diffusion

  ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025)

  Language:Python49839

• shadowpa0327/Palu

  Code for Palu: Compressing KV-Cache with Low-Rank Projection

  Language:Python613

• microsoft/mscclpp

  MSCCL++: A GPU-driven communication stack for scalable AI applications

  Language:C++26643

• bytedance/ABQ-LLM

  An acceleration library that supports arbitrary bit-width combinatorial quantization operations

  Language:C++23225

• efeslab/Nanoflow

  A throughput-oriented high-performance serving framework for LLMs

  Language:Cuda66827

• IST-DASLab/Sparse-Marlin

  Boosting 4-bit inference kernels with 2:4 Sparsity

  Language:Cuda614