verl

verl is a flexible, efficient, and production-ready RL training library for large language models from ByteDance's Seed ...

github

grpo-rl-training

Expert-level guidance for implementing Group Relative Policy Optimization (GRPO) using the Transformer Reinforcement Lea...

github

ray-data

Distributed data processing library for ML and AI workloads. Use Ray Data when: Processing large datasets (>100GB) for M...

github

langchain

The most popular framework for building LLM-powered applications. Use LangChain when: Building agents with tool calling ...

github

tensorrt-llm

NVIDIA's open-source library for optimizing LLM inference with state-of-the-art performance on NVIDIA GPUs. Use TensorRT...

github

instructor

Use Instructor when you need to: Extract structured data from LLM responses reliably Validate outputs against Pydantic s...

github

rigor-reviewer

You are an objective research reviewer for Agent-Native Research Artifacts. You receive an ARA directory path and produc...

github

pytorch-fsdp2

This skill teaches a coding agent how to add PyTorch FSDP2 to a training loop with correct initialization, sharding, mix...

github

mamba

Mamba is a state-space model architecture achieving O(n) linear complexity for sequence modeling. Installation: pip inst...

github

faiss

Facebook AI's library for billion-scale vector similarity search. Use FAISS when: Need fast similarity search on large v...

github

rwkv

RWKV (RwaKuv) combines Transformer parallelization (training) with RNN efficiency (inference). Installation: pip install...

github

ray-train

Ray Train scales machine learning training from single GPU to multi-node clusters with minimal code changes. Installatio...

github

openvla-oft

Fine-tuning and evaluation workflows for OpenVLA-OFT and OpenVLA-OFT+ from the official openvla-oft codebase. Covers bla...

github

phoenix

Open-source AI observability and evaluation platform for LLM applications with tracing, evaluation, datasets, experiment...

github

saelens

SAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polys...

github

speculative-decoding

Use Speculative Decoding when you need to: Speed up inference by 1.5-3.6× without quality loss Reduce latency for real-t...

github

gptq

Post-training quantization method that compresses LLMs to 4-bit with minimal accuracy loss using group-wise quantization...

github

pinecone

The vector database for production AI applications. Use when: Need managed, serverless vector database Production RAG ap...

github

nemo-evaluator

NeMo Evaluator SDK evaluates LLMs across 100+ benchmarks from 18+ harnesses using containerized, reproducible evaluation...

github

flash-attention

Flash Attention provides 2-4x speedup and 10-20x memory reduction for transformer attention through IO-aware tiling and ...

github

transformer-lens

TransformerLens is the de facto standard library for mechanistic interpretability research on GPT-style language models....

github

whisper

OpenAI's multilingual speech recognition model. Use when: Speech-to-text transcription (99 languages) Podcast/video tran...

github

research-manager

You are the Live PM — a post-task research recorder. You run ONLY at the END of a coding session, after the user's reque...

github

trl-fine-tuning

TRL provides post-training methods for aligning language models with human preferences. Installation: pip install trl tr...

github