triple-mu's starred repositories
HunyuanDiT-TensorRT-libtorch
HunyuanDiT with TensorRT and libtorch
HunyuanDiT
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
safetensors-cpp
Header-only safetensors loader and saver in C++
TensorRT-Model-Optimizer
TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization and sparsity. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.
YOLOv8-TensorRT
YOLOv8 using TensorRT accelerate !
optimum-benchmark
🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.
LLMs-from-scratch
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
clash-verge-rev
Continuation of Clash Verge - A Clash Meta GUI based on Tauri (Windows, MacOS, Linux)
lm-evaluation-harness
A framework for few-shot evaluation of language models.
llm-cookbook
面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版
Skywork
Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。
Megatron-LM
Ongoing research training transformer models at scale
TrollStore
Jailed iOS app that can install IPAs permanently with arbitary entitlements and root helpers because it trolls Apple
ThreadPool
A simple C++11 Thread Pool implementation
Open-GroundingDino
This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.
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.