Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
Repositories
Oliver-ss repositories
Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)
Code for paper "Applying Machine Learning to Investigate Long Term Insect-Plant Interactions Preserved on Digitized Herbarium Specimens"
It is drone vision landing based on PX4 SITL Simulation.
Team project for the course: ME555-Advanced Robotics System Design
Duke Machine Learning Winter School 2019
Large-scale model inference.
Unofficial Pytorch code for "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence" in NeurIPS'20. This repo contains reproduced checkpoints.
BY Blog ->
Pipeline Parallelism for PyTorch
Latex code for making neural networks diagrams
Retinaface get 80.99% in widerface hard val using mobilenet0.25.
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
Lightweight coding agent that runs in your terminal
A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer