Results for “beleglage”

Serve LLMs and VLMs with structured outputs, prefix caching, and high throughput using RadixAttention.

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking

RAG Builder with Parallel Document Processing Vector database construction with local embeddings (zero cost) Handles PDF download, text extraction, chunking, and vector database creation Absorbed B5 (Parallel Document Processor) capabilities Use when: building RAG, creating vector database, downloading PDFs, embedding documents, batch processing Triggers: build RAG, create vector database, download PDFs, embed documents, batch PDF processing

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Use this skill whenever a developer wants to turn an idea into a complete, production-ready, end-to-end system plan BEFORE writing any code. Trigger on 'plan this system', 'design the architecture for', 'help me blueprint', 'deep plan for X', 'break this idea into components', 'expand into action points', 'full implementation plan', or when the user pastes a project idea wanting architecture, components, pipelines, and file-level execution mapped out. Casual phrasing also triggers: 'help me think this through end-to-end', 'plan before coding'. Also covers living-workspace patterns: self-improving knowledge bases, reflection loops with auditor agents, four-agent teams, schema-as-code, wiki health scoring. **Resume triggers**: 'where did we leave off', 'continue this plan', 'resume my blueprint' - rehydrates state from disk via SESSION.md/NEXT.md/decisions/. Web research is mandatory every invocation.

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Resolves, generates, and operates on media assets (audio, images, icons, logos, voice, color grades, LUTs) for HyperFrames projects, using a local cache and the HeyGen CLI for free-usage catalog search and TTS.