synxlin

synxlin's Stars

• FoundationVision/VAR

  [NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

  Language:Python4.2k310

• mit-han-lab/qserve

  QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

  Language:Python42622

• mit-han-lab/lmquant

  Language:Python11510

• spcl/QuaRot

  Code for QuaRot, an end-to-end 4-bit inference of large language models.

  Language:Python27120

• mit-han-lab/streaming-llm

  [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

  Language:Python6.6k363

• pest-parser/pest

  The Elegant Parser

  Language:Rust4.6k260

• taocpp/PEGTL

  Parsing Expression Grammar Template Library

  Language:C++1.9k229

• UCLA-VAST/AutoSA

  AutoSA: Polyhedral-Based Systolic Array Compiler

  Language:C++19833

• madhat2r/plaid2text

  Python Scripts to export Plaid transactions and transform them into Ledger or Beancount syntax formatted files.

  Language:Python8919

• ggerganov/llama.cpp

  LLM inference in C/C++

  Language:C++67.2k9.6k

• jbms/beancount-import

  Web UI for semi-automatically importing external data into beancount

  Language:Python392103

• davidepatti/noxim

  Network on Chip Simulator

  Language:C++236122

• flexflow/FlexFlow

  FlexFlow Serve: Low-Latency, High-Performance LLM Serving

  Language:C++1.7k225

• cryptomator/cryptomator

  Cryptomator for Windows, macOS, and Linux: Secure client-side encryption for your cloud storage, ensuring privacy and control over your data.

  Language:Java11.8k1k

• NVlabs/timeloop

  Timeloop performs modeling, mapping and code-generation for tensor algebra workloads on various accelerator architectures.

  Language:C++335101

• mit-han-lab/bevfusion

  [ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

  Language:Python2.3k417

• traveller59/spconv

  Spatial Sparse Convolution Library

  Language:Python1.9k363

• FindDefinition/cumm

  CUda Matrix Multiply library.

  Language:Python709

• FindDefinition/PCCM

  Python C++ Code Manager

  Language:Python14

• nineisprime/optimal-branch

  A light-weight implementation of Edmond's Algorithm in C++

  Language:C++51

• hpcaitech/FastFold

  Optimizing AlphaFold Training and Inference on GPU Clusters

  Language:Python56686

• aqlaboratory/openfold

  Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

  Language:Python2.8k538

• ucb-bar/cosa

  A scheduler for spatial DNN accelerators that generate high-performance schedules in one shot using mixed integer programming (MIP)

  Language:Python7418

• VITA-Group/TENAS

  [ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, Zhangyang Wang

  Language:Python16531

• GATECH-EIC/HW-NAS-Bench

  [ICLR 2021] HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark

  Language:Python10316

• maestro-project/confuciux

  Language:Python315

• maestro-project/gamma

  Language:Python3318

• pku-liang/TENET

  An analytical framework that models hardware dataflow of tensor applications on spatial architectures using the relation-centric notation.

  Language:C++8011

• ipcjs/bilibili-helper

  各种油猴脚本

  Language:JavaScript3.9k328

• mit-han-lab/torchsparse

  [MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

  Language:Cuda1.2k142