Stonesjtu

Stonesjtu's Stars

• ggerganov/llama.cpp

  LLM inference in C/C++

  Language:C++68.2k5474k9.8k

• xai-org/grok-1

  Grok open release

  Language:Python49.6k5742108.3k

• RVC-Boss/GPT-SoVITS

  1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

  Language:Python35.9k2131.3k4.1k

• 2noise/ChatTTS

  A generative speech model for daily dialogue.

  Language:Python32.5k1885583.5k

• myshell-ai/OpenVoice

  Instant voice cloning by MIT and MyShell.

  Language:Python29.9k2162522.9k

• meta-llama/llama3

  The official Meta Llama 3 GitHub site

  Language:Python27.2k2262643.1k

• facebookresearch/audiocraft

  Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

  Language:Python21k2093852.2k

• KindXiaoming/pykan

  Kolmogorov Arnold Networks

  Language:Jupyter Notebook15.1k1134121.4k

• state-spaces/mamba

  Mamba SSM architecture

  Language:Python13.3k995501.1k

• InstantID/InstantID

  InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

  Language:Python10.7k125217785

• vosen/ZLUDA

  CUDA on non-NVIDIA GPUs

  Language:Rust9.8k134178639

• NVIDIA/TensorRT-LLM

  TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

  Language:C++8.7k942k996

• google/gemma.cpp

  lightweight, standalone C++ inference engine for Google's Gemma models.

  Language:C++6k3988509

• google/gemma_pytorch

  The official PyTorch implementation of Google's Gemma models

  Language:Python5.3k3940508

• pytorch/torchtitan

  A native PyTorch Library for large model training

  Language:Python2.6k42178205

• mit-han-lab/llm-awq

  [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

  Language:Python2.5k24187204

• Tele-AI/Telechat

  Language:Python1.8k216199

• HazyResearch/ThunderKittens

  Tile primitives for speedy kernels

  Language:Cuda1.7k292970

• X-LANCE/AniTalker

  [ACM MM 2024] This is the official code for "AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding"

  Language:Jupyter Notebook1.5k6540133

• NVIDIA/cccl

  CUDA Core Compute Libraries

  Language:C++1.3k311.5k164

• tspeterkim/flash-attention-minimal

  Flash Attention in ~100 lines of CUDA (forward pass only)

  Language:Cuda6304654

• X-LANCE/SLAM-LLM

  Speech, Language, Audio, Music Processing with Large Language Model

  Language:Python588214552

• Jokeren/Awesome-GPU

  Awesome resources for GPUs

  49525050

• HazyResearch/aisys-building-blocks

  Building blocks for foundation models.

  39730016

• efeslab/Atom

  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving

  Language:Cuda278101924

• proger/accelerated-scan

  Accelerated First Order Parallel Associative Scan

  Language:Python164878

• NVlabs/cub

  THIS REPOSITORY HAS MOVED TO github.com/nvidia/cub, WHICH IS AUTOMATICALLY MIRRORED HERE.

  Language:Cuda835050

• UofT-EcoSystem/Minuet

  [EuroSys'24] Minuet: Accelerating 3D Sparse Convolutions on GPUs

  Language:Cuda73233

• X-LANCE/PaperReading

  整理各研究方向经典论文

  1030

• Stonesjtu/Awesome-GPU

  Awesome resources for GPUs

  2000