John Senneker's starred repositories
GPU-Puzzles
Solve puzzles. Learn CUDA.
ann-benchmarks
Benchmarks of approximate nearest neighbor libraries in Python
x-transformers
A simple but complete full-attention transformer with a set of promising experimental features from various papers
instructor-embedding
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
sqlite-vss
A SQLite extension for efficient vector search, based on Faiss!
fsdp_qlora
Training LLMs with QLoRA + FSDP
Hybrid-Net
Real-time audio source separation, generate lyrics, chords, beat.
rotary-embedding-torch
Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch
annotated-mamba
Annotated version of the Mamba paper
GPU-Reshape
GPU Reshape (GRS) is an API agnostic instrumentation framework, with instruction level validation.
memory-compressed-attention
Implementation of Memory-Compressed Attention, from the paper "Generating Wikipedia By Summarizing Long Sequences"