Pinned Repositories
crypto11
Implement elliptic curve secp256k1
cuda
Mirror of Fork of nvida cuda docker containers repository
cutlass
CUDA Templates for Linear Algebra Subroutines
cxxopts
Lightweight C++ command line option parser
ebiten-virtualpad
virtualpad package for ebiten
gradient-spinner-demo
fun little Playground in Swift 3 demonstrating how to create an animated spinner with a gradient background
Llama-2-Onnx
MGBox2
Simple, quick iOS tables, grids, and more
UISS
UIAppearance Stylesheets
pdtgct's Repositories
pdtgct/UISS
UIAppearance Stylesheets
pdtgct/gradient-spinner-demo
fun little Playground in Swift 3 demonstrating how to create an animated spinner with a gradient background
pdtgct/Llama-2-Onnx
pdtgct/MGBox2
Simple, quick iOS tables, grids, and more
pdtgct/crypto11
Implement elliptic curve secp256k1
pdtgct/cuda
Mirror of Fork of nvida cuda docker containers repository
pdtgct/cutlass
CUDA Templates for Linear Algebra Subroutines
pdtgct/cxxopts
Lightweight C++ command line option parser
pdtgct/ebiten-virtualpad
virtualpad package for ebiten
pdtgct/iProxy
Let's you connect your laptop to the iPhone to surf the web.
pdtgct/LXReorderableCollectionViewFlowLayout
Extends `UICollectionViewFlowLayout` to support reordering of cells. Similar to long press and pan on books in iBook.
pdtgct/ml-notebooks
pdtgct/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
pdtgct/pkcs11
pkcs11 wrapper for Go
pdtgct/pop
Extensible iOS and OS X animation library.
pdtgct/foundation-model-benchmarking-tool
Foundation model benchmarking tool. Run any model on Amazon SageMaker and benchmark for performance across instance type and serving stack options.
pdtgct/huggingface-blog
Public repo for HF blog posts
pdtgct/json
JSON for Modern C++
pdtgct/lightllm
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
pdtgct/lmdeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
pdtgct/NVTX
The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resources in your applications.
pdtgct/PartitionedLongBench
https://github.com/THUDM/LongBench data partitioned into Retrieval Augmented Generation (RAG) segments for performance testing.
pdtgct/roberta-ner
RoBERTa-family Named Entity Recognition training
pdtgct/Specs
A repository of CocoaPods (cocoapods.org) specifications.
pdtgct/svg-morph
morph animation between two svg path arrays
pdtgct/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.
pdtgct/text-generation-inference
Large Language Model Text Generation Inference
pdtgct/triton
Development repository for the Triton language and compiler
pdtgct/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
pdtgct/XBPageCurl
A decent page curl transition for iOS.