xingjinglu

xingjinglu's Stars

• AUTOMATIC1111/stable-diffusion-webui

  Stable Diffusion web UI

  Language:Python144k1.1k7.7k27k

• CompVis/stable-diffusion

  A latent text-to-image diffusion model

  Language:Jupyter Notebook68.6k55971610.2k

• LAION-AI/Open-Assistant

  OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

  Language:Python37.1k4311.6k3.2k

• OAI/OpenAPI-Specification

  The OpenAPI Specification Repository

  Language:Markdown29.1k8432.3k9.1k

• facebook/folly

  An open-source C++ library developed and used at Facebook.

  Language:C++28.5k1k1.2k5.6k

• apple/ml-stable-diffusion

  Stable Diffusion with Core ML on Apple Silicon

  Language:Python17k142252950

• triton-lang/triton

  Development repository for the Triton language and compiler

  Language:C++13.6k1971.5k1.7k

• temporalio/temporal

  Temporal service

  Language:Go12.2k1021.3k851

• facebookresearch/xformers

  Hackable and optimized Transformers building blocks, supporting a composable construction.

  Language:Python8.7k77569622

• gperftools/gperftools

  Main gperftools repository

  Language:C++8.5k3621.3k1.5k

• THUDM/GLM-130B

  GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

  Language:Python7.7k99198608

• facebookincubator/AITemplate

  AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

  Language:Python4.6k82244372

• oneapi-src/oneDNN

  oneAPI Deep Neural Network Library (oneDNN)

  Language:C++3.6k1801.3k1k

• sovrasov/flops-counter.pytorch

  Flops counter for convolutional networks in pytorch framework

  Language:Python2.8k1598306

• herumi/xbyak

  A JIT assembler for x86/x64 architectures supporting MMX, SSE (1-4), AVX (1-2, 512), FPU, APX, and AVX10.2

  Language:C++2.1k11594277

• microsoft/Megatron-DeepSpeed

  Ongoing research training transformer language models at scale, including: BERT & GPT-2

  Language:Python1.9k24182344

• skarupke/flat_hash_map

  A very fast hashtable

  Language:C++1.7k7341185

• pytorch/torchdynamo

  A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

  Language:Python1k45567124

• python/pyperformance

  Python Performance Benchmark Suite

  Language:Python87061117176

• stochasticai/x-stable-diffusion

  Real-time inference for Stable Diffusion - 0.88s latency. Covers AITemplate, nvFuser, TensorRT, FlashAttention. Join our Discord communty: https://discord.com/invite/TgHXuSJEk6

  Language:Jupyter Notebook553142135

• ROCm/composable_kernel

  Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators

  Language:C++32125229129

• amirgholami/ZeroQ

  [CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework

  Language:Python274172656

• kssteven418/I-BERT

  [ICML'21 Oral] I-BERT: Integer-only BERT Quantization

  Language:Python23043132

• WoosukKwon/retraining-free-pruning

  [NeurIPS 2022] A Fast Post-Training Pruning Framework for Transformers

  Language:Python17361927

• zengkid/pdf-books

  :books: PDF 书籍库

  Language:Java1220059

• astojanov/Clover

  Clover: Quantized 4-bit Linear Algebra Library

  Language:C++110515

• kssteven418/LTP

  [KDD'22] Learned Token Pruning for Transformers

  Language:Python9331017

• renzibei/fph-table

  Flash Perfect Hash Table: an implementation of a dynamic perfect hash table, extremely fast for lookup

  Language:C++42355

• masahi/tvm-winograd

  Test winograd convolution written in TVM for CUDA and AMDGPU

  Language:Python40402

• kssteven418/Q-ASR

  [ICASSP'22] Integer-only Zero-shot Quantization for Efficient Speech Recognition

  Language:Jupyter Notebook30512