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.
Repository Index
97,836 visible repositories in the index
25–48 of 501 · Most stars
A hyperparameter optimization framework
- python
- machine-learning
- parallel
- distributed
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
- autonomous-research
- citation-verification
- llm-agents
- multi-agent-debate
The most complete open-source, self-hosted Agentic Trading OS—AI research, Python strategies, factor discovery, backtesting, optimization, paper/live multi-asset execution, risk controls, monitoring, MCP, and multi-tenant SaaS in one auditable stack.
- quantitative-finance
- quant
- python
- fintech
Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals
- python
- profiling
- performance-analysis
- cpu-profiling
Translated🔍 Hands-on LLM Application Development, Part 1: A Full-Stack Guide to RAG Technology. Read online at: https://datawhalechina.github.io/all-in-rag/
- embedding
- kimi-k2
- langchain
- llama-index
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
- deep-learning
- pytorch
- grad-cam
- visualizations
Retrieval and Retrieval-augmented LLMs
- embeddings
- information-retrieval
- llm
- sentence-embeddings
GEO-first SEO skill for Claude Code. Comprehensive AI search optimization for any website — citability scoring, AI crawler analysis, brand authority, schema markup, platform-specific optimization, and PDF reports. If you want learn how to sell this to real businesses, check out the skool community
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
- machine-learning
- experiment-track
- deep-learning
- keras
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
An elegant PyTorch deep reinforcement learning library.
- pytorch
- policy-gradient
- dqn
- double-dqn
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
- cloud-computing
- deep-learning
- gpu
- hyperparameter-tuning
Fast and Accurate ML in 3 Lines of Code
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
- wandb
- reinforcement-learning
- pytorch
- python
Hackable and optimized Transformers building blocks, supporting a composable construction.
q - Run SQL directly on delimited files and multi-file sqlite databases
- python
- sql
- cli
- command-line-tool
Build, Manage and Deploy AI/ML Systems
- machine-learning
- model-management
- ai
- ml
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.com/pymc-devs/pytensor
The research engine that gives you an unfair advantage. Run thousands of trading ideas before others finish one.
- backtesting
- trading
- algorithmic-trading
- trading-strategies
Python SQL Parser and Transpiler
- transpiler
- sql
- python
- parser
Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.