honglu2875
Follow
Stars
A machine learning compiler for GPUs, CPUs, and ML accelerators
đź“ś Extract meaningful content from the chaos of a web page
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
High-Performance Symbolic Regression in Python and Julia
lightweight, standalone C++ inference engine for Google's Gemma models.
A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.
Transform Python source code into its most compact representation
Auto configurations for Language Server for vim-lsp
Textual Inputs is a collection of input widgets for the Textual TUI framework 🔡
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Weighted MinHash implementation on CUDA (multi-gpu).
LLM verified with Monte Carlo Tree Search
Playing Pokemon Red with Reinforcement Learning
A Python framework for high performance GPU simulation and graphics
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilizatio…
A high-throughput and memory-efficient inference and serving engine for LLMs
A game theoretic approach to explain the output of any machine learning model.
PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.
Harness the power of ChatGPT inside the GDB or LLDB debugger!
Little article showing how to load pytorch's models with linear memory consumption
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Port of OpenAI's Whisper model in C/C++
Neural baselines for finding and fixing single token bugs in Python