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…
Reference for the neuron-explorer profile schema (the parquet tables produced when neuron-explorer view/ingest processes a profile). Use when the user asks "what tables are in the profile", "what fields are in ", "where does this field come from", "where can I find matmul/source-line info in the schema", or wants to…
Port a HuggingFace model to NeuronX Distributed Inference for AWS Trainium/Inferentia. Use when the user says "port model", "autoport", "convert to neuron", "compile for trainium", or invokes /neuron-framework-autoport. Handles the full workflow: knowledge base analysis, architecture analysis, NeuronX implementation…
Verifies functional equivalence between two implementations of the same model using a hierarchical 8-stage algorithm. Orchestrates model tree comparison, component-level R-ratio testing, E2E logit comparison, and distributional checks. Use when porting models between frameworks, hardware targets, or precision regimes…
This skill guides debugging NKI compilation errors on Neuron hardware. Use when encountering "compiler error on device", "debug NKI kernel", "test kernel on trn2/trn3", "neuronx-cc compilation failed", "validate kernel on hardware", "run kernel on trainium", or asking "how to debug NKI compilation errors on device".
Research NKI documentation for API lookups, tutorials, error codes, architecture, and optimization guides. Use when user asks "what does do", "how to do ", "what is error ", "NKI signature", "find NKI tutorial for ", "look up ", or needs any NKI documentation reference.
Query and analyze NKI kernel profile data from neuron-explorer parquet files. Supports SQL queries via the neuron-explorer API and Python on parquet for advanced analysis. Works locally on trainium with NEFF/NTFF files on disk. Querying: start neuron-explorer, ingest profiles, run SQL against tables (Summary…
This skill guides using the cli to generate NKI kernel profiles (NEFF + NTFF pairs) to analyze performance on Neuron hardware. Use when encountering "profile kernel", "capture execution trace", "generate NEFF", "get summary-json", or asking "how to profile NKI kernel".
Guide for writing and modifying NKI kernels. Covers new kernel creation from PyTorch/NumPy/natural language, editing existing kernels, adding shape/dtype support, refactoring tiling strategies, and implementing new features in NKI code. Use when user says "write NKI kernel", "convert PyTorch to NKI", "translate numpy…