vlm-run

Use the mm CLI to index, explore, query, and extract content from multimodal directories containing images, videos, PDFs, code, and other files. Triggers: exploring a directory's contents, listing/finding files by type or size, extracting text from PDFs, getting image metadata, searching across file contents, counting tokens, viewing directory trees, extracting PDF page mosaics, video keyframe extraction, 'what files are in this folder', 'find all images', 'show me the PDFs', 'how much storage do videos use', 'extract text from this PDF', 'search documents for X', 'analyze this directory', 'how many tokens', 'show the tree'.

Use the VLM Run CLI (`vlmrun`) to interact with Orion visual AI agent. Process images, videos, and documents with natural language. Triggers: image understanding/generation, object detection, OCR, video summarization, document extraction, image generation, visual AI chat, 'generate an image/video', 'analyze this image/video', 'extract text from', 'summarize this video', 'process this PDF'.

Use the mm CLI and Python API to index, explore, query, and extract content from multimodal directories containing images, videos, PDFs, code, and other files. Triggers: exploring a directory's contents, listing/finding files by type or size, extracting text from PDFs, getting image metadata, searching across file contents, counting tokens, viewing directory trees, extracting PDF page mosaics, video keyframe extraction, building VLM prompts, encoding media, audio transcription, 'what files are in this folder', 'find all images', 'show me the PDFs', 'how much storage do videos use', 'extract text from this PDF', 'search documents for X', 'analyze this directory', 'how many tokens', 'show the tree', 'build a VLM prompt', 'transcribe audio', 'encode this image'.

VLM benchmark CLI — run, compare, and reproduce VLM inference benchmarks. Use when the user wants to: (1) benchmark a VLM model's throughput, latency, or VRAM usage, (2) compare results across models or configs, (3) choose or configure a backend (vLLM Docker, vLLM native, Ollama, SGLang, cloud API), (4) run text-only LLM benchmarks via HF dataset text columns, (5) look up model-specific --serve-args, or (6) debug server startup or GPU detection issues. Triggers on: vlmbench, VLM benchmarking, OCR model evaluation, inference throughput, tokens/sec, TTFT, TPOT, VRAM, text benchmark.