Modular is an integrated, composable suite of tools that simplifies your AI infrastructure so your team can develop, deploy, and innovate faster.
Modular Inc publishes skills that help AI agents write Mojo code, including syntax conventions, GPU programming on NVIDIA, AMD and Apple silicon, and Python interoperability. Its skills also cover serving and operating models on the MAX platform, such as benchmarking throughput and latency, profiling GPU utilization, importing new Hugging Face architectures, debugging output mismatches, and migrating code from the V2 graph API to ModuleV3.
Skills
11 skills · 208 stars · NOASSERTION
Benchmark Model Benchmark a model served on MAX with the `max benchmark` command: measure throughput (tokens/sec)…
Debug Model Debug a MAX model that loads, compiles, serves, and generates tokens but whose output disagrees w…
Eval Model Measures the task accuracy of text models served by MAX using standard benchmarks such as GSM8K,…
Import Model Use when importing a new model architecture into MAX from a Hugging Face model ID.
Migrate Max V2 To V3 Use when migrating a MAX model from the V2 graph API (max.nn, TensorValue, explicit Graph constru…
Mojo Gpu Fundamentals The basics of how to program GPUs using Mojo.
Mojo Python Interop Aids in writing Mojo code that interoperates with Python using current syntax and conventions.
Mojo Syntax Help to write Mojo code using current syntax and conventions.
New Modular Project Creates a new Mojo or MAX project.
Profile Model Profile a model running on MAX to find where it spends time and whether the GPU is saturated.
Serve Model Serve a model with MAX's `max serve` command: set up the environment (pixi or uv with the max-nig…