Stars
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.
Kodu is an autonomous coding agent that lives in your IDE. It is a VSCode extension that can help you build your dream project step by step by leveraging the latest technologies in automated coding…
Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.
[ICLR 2024] SWE-bench: Can Language Models Resolve Real-world Github Issues?
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
[NeurIPS'24 Spotlight] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 whil…
16-fold memory access reduction with nearly no loss
SGLang is a fast serving framework for large language models and vision language models.
andy-yang-1 / sglang
Forked from sgl-project/sglangSGLang is a fast serving framework for large language models and vision language models.
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Get up and running with Llama 3.3, Phi 4, Gemma 2, and other large language models.
JDiffusion is a diffusion model library for generating images or videos based on Diffusers and Jittor.
Fitten Code AI Programming Assistant for Neovim
LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
LLM powered development for VSCode
LSP server leveraging LLMs for code completion (and more?)
Flow-Guided Feature Aggregation for Video Object Detection
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
High-performance, scalable time-series database designed for Industrial IoT (IIoT) scenarios
This is an accurate implementation for IoU loss between two rotated polygons. This algorithm is accurate and differential, but there is no support for cuda now. In https://github.com/lilanxiao/Rota…
The code of RoIAttn R-CNN
[ECCV22] BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering (Jittor)
Fast and memory-efficient exact attention
OpenLLaMA-Chinese, a permissively licensed open source instruction-following models based on OpenLLaMA
A unified framework for 3D content generation.
Official implementation of "Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation"
Segment-Anything + 3D. Let's lift anything to 3D.