Results for “gpu”

Write, review, refactor, and optimize Slang shader code for graphics, compute, tessellation, and ray tracing pipelines with cross-compilation support.

Quantize large language models to 4-bit precision using activation-aware weight quantization, reducing memory footprint and speeding up inference with minimal accuracy loss.

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware, with backend selection between vLLM, Transformers, and accelerate.

Write, review, and migrate code using NVIDIA DALI's imperative dynamic-mode API for efficient data loading and preprocessing.

Run ML training and batch jobs across multiple clouds with automatic cost optimization, spot instance recovery, and unified orchestration.

Train large language models (7B-70B+) with RLHF using PPO, GRPO, DPO, and other algorithms, accelerated by Ray and vLLM for distributed multi-GPU setups.

Add distributed training support to any PyTorch script with minimal code changes using a unified API for DDP, DeepSpeed, FSDP, and mixed precision.

Launch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.

Selects, configures, deploys, verifies, debugs, or tears down a VSS profile (base, search, lvs, warehouse, edge) for NVIDIA's video search and summarization stack.

Finetune the NV-Generate-CTMR MAISI VAE/autoencoder on user-supplied CT or MRI NIfTI volumes using a staged config and datalist workflow.

Estimates GPU memory required to load Safetensors or GGUF model weights for inference from the Hugging Face Hub using HTTP Range requests, without downloading weights locally.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies for maximum GPU efficiency.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on limited GPU memory.

Reference guide for evaluating LLM-generated translations between CUDA and OpenMP, covering memory model mapping, kernel launch patterns, shared memory, atomics, and common failure modes.

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

Pattern for creating new Colab notebooks. Trigger when: (1) Creating a new notebook for experiments, (2) Adding notebook-based functionality, (3) Agent or validation notebooks, (4) Any notebook that uses GPU training infrastructure.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on consumer GPUs.

Convert and quantize models to GGUF format for efficient CPU/GPU inference with llama.cpp, supporting 2-8 bit quantization and Apple Silicon acceleration.

Runs 150+ AI apps in the cloud via the infsh CLI, covering image generation, video creation, search, 3D, and social automation without needing a GPU.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Adds autotuning to CuTile kernels using the exhaustive_search API with a tune-once/cache/direct-launch pattern, covering occupancy-only and complex tile-size search spaces.

Provides idiomatic PyTorch patterns and best practices for building robust, efficient, and reproducible deep learning applications, covering model architecture, training loops, data pipelines, and checkpointing.

Organizes PyTorch code with a Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks, and minimal boilerplate. Scales from laptop to supercomputer with the same code.

Deploy a standalone RT-VLM dense-captioning microservice and exercise its REST API endpoints for file upload, caption generation, streaming, chat completions, and Kafka integration.

Run computational biology tools for protein structure prediction, design, docking, and molecular dynamics on managed cloud GPUs via REST API or MCP server.

Pretrains large language models from scratch using PyTorch-native distributed training with 4D parallelism (FSDP2, TP, PP, CP) and Float8 support on H100 GPUs.

Provides practical guidance for training Mixture-of-Experts Vision-Language Models in Megatron Bridge, comparing FSDP and 3D-parallel approaches with lessons from recent multimodal experiments.

Generates synthetic body MRI volumes using NVIDIA's NV-Generate-CTMR rflow-mr model. Wraps the upstream diffusion inference pipeline with config staging, output validation, and NIfTI volume summarization.

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.

Guides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.

Connect to the MAXIA AI-to-AI marketplace on Solana to discover, buy, and sell AI services, earn USDC, and access crypto intelligence, DeFi yields, sentiment analysis, and rug detection tools.

Provides battle-tested PyTorch training recipes for LLMs, vision, diffusion, and biomedical domains, covering training loops, optimizer selection, LR scheduling, mixed precision, and debugging.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.