Autonomous agent for porting HuggingFace models to NeuronX Distributed Inference (NXDI) for AWS Trainium/Inferentia hardware. Accepts model parameters and executes the full porting workflow: knowledge base analysis, architecture analysis, implementation, compilation, inference testing, and validation. Context: User…
Autonomous agent for porting HuggingFace models to the vLLM-Neuron Trainium2 backend. Accepts a model name and HuggingFace model ID, then executes the full porting workflow: architecture research, code generation, model registration, and validation. Context: User wants to port Yi to vLLM-Neuron user: "Port yi…
Verify functional equivalence between a source (reference) and target (ported) model implementation using the 8-stage equivalence pipeline. Covers model tree comparison, component-level R-ratio testing, E2E logit comparison, distributional checks, and downstream evaluation. Use when porting models between frameworks…
Unified NKI kernel development agent. CRITICAL: Before writing any NKI code, read the language constraint reference at skills/neuron-nki-writing/references/nki-language-constraint.md for the required API patterns and reference kernel template. Context: Kernel won't compile user: "Fix these compilation errors in my…
Use this agent for autonomously debugging and fixing NKI kernel compilation errors. This agent analyzes compiler errors, searches for fixes in documentation and code examples, applies corrections following the principle of simplicity over performance, and validates the fixes. Context: User has a kernel with…
Profile and analyze NKI kernels on Neuron hardware. Captures execution traces, ingests profiles, computes performance bounds, identifies bottleneck engines, and runs investigations to localize inefficiencies to NKI source lines. Context: User wants end-to-end profiling and analysis user: "Profile and analyze my matmul…
Use this agent for writing new NKI kernels or modifying existing ones. Handles translation from PyTorch/NumPy/natural language, adding shape/dtype support, refactoring tiling strategies, and implementing new features in NKI code. Follows Beta 2 API patterns. Context: User has PyTorch code and wants NKI version user…