Results for “finite-state-machine”

Trains, evaluates, exports, and runs inference for FastFoundationStereo (FFS) stereo depth estimation models, a distilled variant of FoundationStereo with lower latency.

Finetunes the NV-Generate-CTMR MR-brain diffusion UNet from user-supplied NIfTI training volumes using a wrapper that stages configs and delegates to upstream scripts.

Train and run Mamba state-space models with O(n) complexity, achieving faster inference and longer context than Transformers.

Measures distributional similarity between original GAN-generated images and their semantically manipulated counterparts using the Fréchet Inception Distance (FID) metric.

Quantize LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss using bitsandbytes. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends for deployment with vLLM or HuggingFace Transformers.

Classifies situations into 256 binary states and maps each to a prescribed action, reporting the pattern, decimal, name, range, and action to execute.

Evaluates computational throughput and real-time efficiency of embedded CPU and GPU platforms by measuring peak FLOPS via a matrix rotation kernel and assessing inference latency and power consumption on a robotic vision pipeline.