Results for “nvidia”

Subquadratic Attention Harvard NVIDIA Arya Tschand Yaosheng Fu Vijay Janapa Reddi Splitting quadrati

The English summary is being prepared. Showing the original description.

Cold start — every GPU, every model size GPU Model ZSE vLLM Speedup NVIDIA T4 (16 GB) Qwen2.

The English summary is being prepared. Showing the original description.

Architecte Agent IA — Conçoit et déploie des agents IA (Hermes, Claude Code, n8n, NVIDIA NIM). Expert en architecture multi-agents, orchestration, et intégration de workflows IA.

The English summary is being prepared. Showing the original description.

Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII Tespit and content policy enforcement, and the Guardrails AI framework for structured output validation. The guardrails system intercepts both user inputs (blocking injection attempts, stripping PII, ...

The English summary is being prepared. Showing the original description.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

The English summary is being prepared. Showing the original description.

Build premium scroll-driven web pages and product showcases inspired by high-end app, hardware, and product interaction patterns. Use for Raycast-like, Apple-like, NVIDIA-like, RTX/GPU, SaaS, AI browser, parallax, sticky scroll, pinned reveal, Three.js GLB model, Web Audio sound effect, responsive accessibility, and performance-safe frontend requests.

The English summary is being prepared. Showing the original description.

AI-assisted label triage for NVIDIA/NemoClaw issues and PRs. Reads triage-instructions.md at runtime for consistent label guidance. Supports single-item mode (give it a number) and batch mode (fetches up to 50 unlabeled open items). On approval, applies labels and an optional triage comment via gh CLI, then logs the session to the daily-rhythm activity folder. Trigger keywords - triage, label issues, suggest labels, batch triage, triage issue, triage PR, label this, what labels.

The English summary is being prepared. Showing the original description.

INVOKE THIS SKILL when creating, reading, updating, or deleting Arize AI integrations. Covers listing integrations, creating integrations for any supported LLM provider (OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM, custom), updating credentials or metadata, and deleting integrations using the ax CLI.

The English summary is being prepared. Showing the original description.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

The English summary is being prepared. Showing the original description.