Pinned Repositories
ChatTTS
ChatTTS is a generative speech model for daily dialogue.
cmake-learn
CMake turtorial sample code
cudaMaster
notes for CUDA
cudaVStemplate
Visual Studio2022 cuda11.6 win10
gpu_computing_in_robotics
ubuntu 18.04.2 cuda-10.0
LabelFusion
rapyuta
rapyuta remote PC
resnet-torch
resnet-torch for partial discharge classification
screenshot-to-code
Drop in a screenshot and convert it to clean HTML/Tailwind/JS code
tb3_aprilTag
tb3_aprilTag simulation
YuehChuan's Repositories
YuehChuan/ChatTTS
ChatTTS is a generative speech model for daily dialogue.
YuehChuan/unitreeG1_ik
Unitree G1 Inverse kinematics
YuehChuan/barkour_robot
Barkour Robot: Agile Quadruped Robots by Google DeepMind
YuehChuan/cutlass-kernels
YuehChuan/dclm
DataComp for Language Models
YuehChuan/DeepEP
DeepEP: an efficient expert-parallel communication library
YuehChuan/GaLore
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
YuehChuan/gpu-benches
collection of benchmarks to measure basic GPU capabilities
YuehChuan/gpuocelot
GPUOcelot: A dynamic compilation framework for PTX
YuehChuan/groq-frontend-base
Base project for bootstrapping frontend projects
YuehChuan/HDMI
YuehChuan/instructor
structured outputs for llms
YuehChuan/jCap
captions with Breeze-ASR-25-whispercpp
YuehChuan/lerobot-mujoco-tutorial
lerobot-mujoco-tutorial
YuehChuan/llama3.cuda
llama3.cuda is a pure C/CUDA implementation for Llama 3 model.
YuehChuan/llamafile
Distribute and run LLMs with a single file.
YuehChuan/llm.c
LLM training in simple, raw C/CUDA
YuehChuan/minions
Let's do something evil
YuehChuan/mirage
A multi-level tensor algebra superoptimizer
YuehChuan/nanoVLM
The simplest, fastest repository for training/finetuning small-sized VLMs.
YuehChuan/physicSim
Rotating Sphere
YuehChuan/rag-from-scratch
YuehChuan/rag_demo
A Retrieval-Augmented Generation (RAG) demo using groq with DeepSeek, ChromaDB
YuehChuan/sglang
SGLang is a fast serving framework for large language models and vision language models.
YuehChuan/tapnet
Tracking Any Point (TAP)
YuehChuan/uffe
A sub-100 lines, self-aware, independent, somewhat capabable LLM Agent with long term memory
YuehChuan/unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
YuehChuan/uvgRTP
An open-source library for RTP/SRTP media delivery
YuehChuan/xdp-tutorial
XDP tutorial
YuehChuan/yalantinglibs
A collection of modern C++ libraries, include coro_rpc, struct_pack, struct_json, struct_xml, struct_pb, easylog, async_simple