julian-q

CS @ Stanford

Pinned Repositories

auto-compile
Language:Python11
BIGCHAIR
BIGCHAIR: BImodal Graph-CHAracter learnIng for Retrieval. Stanford CS 224N final project by Pino Cholsaipant, Sidney Hough, + Julian Quevedo.
Language:Jupyter Notebook1 2 00
dotfiles
Language:Vim Script10
facecam
Language:Python20
fmri-analysis
Graph Attention Transformer Encoder: QKV attention mechanism for GNNs.
Language:Python0 1 01
hgcn
Increased-Efficiency Hyperbolic Graph Convolutional Networks with PyTorch Geometric.
Language:Python1 0 00
kgene
Knowledge graph extraction from webcrawled plaintext.
Language:Julia4 2 80
laser-control
Automatic laser power stabilization using a motorized waveplate mount.
Language:Jupyter Notebook1 1 01
magtrack
An Arduino-based device for characterizing magnetic shielding.
Language:C++1 1 00
policy-gradient
Reinforcement Learning: A NumPy implementation of two simple policy gradient algorithms.
Language:Python0 1 00

julian-q's Repositories

julian-q/kgene
Knowledge graph extraction from webcrawled plaintext.
Language:Julia4 2 80
julian-q/facecam
Language:Python20
julian-q/auto-compile
Language:Python11
julian-q/BIGCHAIR
BIGCHAIR: BImodal Graph-CHAracter learnIng for Retrieval. Stanford CS 224N final project by Pino Cholsaipant, Sidney Hough, + Julian Quevedo.
Language:Jupyter Notebook1 2 00
julian-q/dotfiles
Language:Vim Script10
julian-q/hgcn
Increased-Efficiency Hyperbolic Graph Convolutional Networks with PyTorch Geometric.
Language:Python1 0 00
julian-q/laser-control
Automatic laser power stabilization using a motorized waveplate mount.
Language:Jupyter Notebook1 1 01
julian-q/fmri-analysis
Graph Attention Transformer Encoder: QKV attention mechanism for GNNs.
Language:Python0 1 01
julian-q/GradCache
Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint
Language:Python0 0 00
julian-q/hugo-PaperMod
A fast, clean, responsive Hugo theme.
Language:HTML0 0 00
julian-q/policy-gradient
Reinforcement Learning: A NumPy implementation of two simple policy gradient algorithms.
Language:Python0 1 00
julian-q/ArCHer
Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"
Language:Python
julian-q/attention_experiments
Language:Cuda
julian-q/composer
Train neural networks up to 7x faster
julian-q/cs140e-24win
all class materials for 140e
julian-q/cs149gpt
Language:Python
julian-q/FasterTransformer
Transformer related optimization, including BERT, GPT
julian-q/FlexGen
Running large language models on a single GPU for throughput-oriented scenarios.
julian-q/gemm
Improving GEMM performance with language models
Language:Python
julian-q/graph-meta-rl-for-amod
Official implementation of "Graph Meta-Reinforcement Learning for TransferableAutonomous Mobility-on-Demand"
Language:Python
julian-q/GraphGPT
Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️‍♂️
julian-q/kliu.io
A blog.
julian-q/llm-awq
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
julian-q/object-oriented-NN
Object-oriented neural network built from scratch with NumPy.
Language:Jupyter Notebook1 0
julian-q/plants
Exploring Lindenmayer systems. BIO 20Q project by Pino Cholsaipant + Julian Quevedo.
Language:JavaScript1 0
julian-q/pytorch_geometric
Graph Neural Network Library for PyTorch
Language:Python0 0
julian-q/sketches
programmatic animations with processing
Language:JavaScript1 0
julian-q/smoothquant
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
Language:Python
julian-q/vector-fields
A simple vector field / differential equation plotter with Euler's method solution trajectories.
Language:JavaScript1 0
julian-q/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs