Results for “tunit”

Train, evaluate, export, distill, quantize, or run inference for a TAO DINO 2D object detector using transformer-based detection with denoising training and multi-scale features.

Train, evaluate, distill, quantize, export, and run inference for RT-DETR object detection models using NVIDIA TAO.

Train, evaluate, export, prune, and run inference for PointPillars 3D object detection models from LiDAR point clouds using NVIDIA TAO.

Build, refactor, or review macOS menubar apps that use Tuist and SwiftUI, with a focus on Tuist-first workflows, strict architecture boundaries, and reliable local launch scripts.

Fine-tune instruction-following LLMs with Unsloth's optimized SFTTrainer, covering dataset formatting, chat templates, training configuration, and thinking-model patterns.

Trains, evaluates, exports, prunes, quantizes, retrains, and runs inference for OCDNet scene text detection models using TAO, detecting arbitrary-oriented text regions in natural images.

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.

Train, evaluate, export, and run inference for monocular depth estimation models using Metric Depth Anything v2 or Relative Depth Anything architectures via the TAO toolkit.

Write high-performance GPU kernels using cuTile's tile-based programming model with validation and optimization, including deep agent orchestration for complex multi-kernel tasks.

Trains vision transformers via self-distillation without labels for self-supervised visual representation learning, and supports export and inference of NVDINOv2 backbones.

Fine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.