Tag
Explore by tags
Provides curated ComfyUI workflow templates and subgraph blueprints that package reusable node graphs, preview assets, and publishing pipelines for image/video generation. Includes a browsable Astro site with i18n, CI-driven sync/publish scripts, and PyPI packaging for easy distribution.
Measures generative AI inference performance with token-level metrics (TTFT, inter-token latency), latency, and throughput under realistic traffic patterns. Provides a multiprocess engine, real-time TUI dashboard, extensible plugins, and integrations for telemetry and result uploads, aimed at inference benchmarking and capacity planning.
Provides a modular full-stack reinforcement learning stack to train and evaluate long-horizon, multi-turn tool-use LLM agents, including a performant trainer, a Tinker-compatible backend, agent orchestration, and Gymnasium-style environments for task design.
Runs Cloudflare Workers and Durable Objects on self-hosted nodes, storing each object as an independently replicated SQLite database in an S3-compatible bucket—enabling per-object sharding, hibernation, and ownership via object-storage compare-and-swap without a central control plane.
A PyTorch DTensor-native SPMD library for training and fine-tuning LLMs, VLMs, diffusion and retrieval models. Integrates with Hugging Face for day-0 model support, provides YAML-driven recipes, DTensor/FSDP2 parallelism and NVIDIA-optimized kernels (Transformer Engine, DeepEP, FlexAttn).
Practical, full-stack tutorial for building Retrieval-Augmented Generation (RAG) systems—covers data preprocessing, vector embedding and indexing, hybrid and multimodal retrieval, generation integration, evaluation and production-ready engineering. Includes hands-on projects and examples for developers with Python experience.
Evaluates and optimizes AI agents and language models in containerized environments, supporting large-scale parallel benchmarks and RL rollouts. Integrates with third‑party providers for thousands of parallel environments and serves as the official harness for Terminal‑Bench.
Coordinates multiple AI coding agents and persists work state in git-backed hooks; provides convoy-based work tracking, an AI coordinator (Mayor), agent lifecycle/watchdog tooling, and a merge/refinery workflow for reliable multi-agent code work.
Gateway that pools multiple AI subscription accounts and issues platform API keys while handling authentication, token-level billing, load balancing, rate limits, and per-user/account concurrency—enables shared subscriptions for Claude, OpenAI, Gemini and Grok.
Runs background coding agents in isolated sandboxes to autonomously handle development tasks, create pull requests, and integrate with Slack, GitHub, Linear and webhooks. Supports multiplayer sessions, multiple LLM providers, fast startup via snapshots and prebuilt images; designed for single-tenant deployments.
Provides a catalog of NVIDIA-verified, portable “skills” — instruction sets that teach AI agents how to use NVIDIA libraries, models and platform tools. Each skill is published with detached signatures and evaluation artifacts for verifiable reuse in agent workflows.