CUDA matrix multiplication benchmarking on Jetson Orin Nano. Four implementations, three power modes, five matrix sizes. 99.5% mathematical validation. C++/CUDA and Python.

Dashboard for AI Studio, Open Source Continuous Inference | Deepseek-R1, Qwen2.5, Llama3.1 | 4xRTX-5090 inside PRU2500, 2xH100 inside PRU2500, 8xMI210 in SuperMicro

LLM benchmarking, GPU workload orchestration backend server | Deepseek-R1, Qwen2.5, Llama3.1 | 4xRTX-5090 inside PRU2500, 2xH100 inside PRU2500, 8xMI210 in SuperMicro

Automated game testing and GPU Cooling Tester Evaluation with reproducible measurements and profile authoring

Standalone LLM inference benchmarking pipelines on AMD GPUs using ROCm, vLLM, MAD, and data visualization scripts.

Hands-on Jupyter notebooks for deep learning with TensorFlow, covering fundamental concepts, model training, and applied tabular projects.

Plots GPU benchmarks across user-selected axes and highlights the Pareto frontier to help builders choose hardware for local AI inference without editorial bias.

Artifact-backed LLM serving performance lab for vLLM baselines, official metrics, GuideLLM checks, and SGLang/PD scaffolding

benchHUB is a Python-based project to parse, aggregate, and visualize system and performance benchmarks. It includes a Streamlit dashboard to display and compare results.

Reproducible GPT-2 distributed-training benchmarks on 1-8 V100 GPUs using Slurm, PyTorch, DeepSpeed, NCCL, NVTX, and Nsight Systems.

Measured CUDA graphs trade-off in vLLM 0.23 on H100: per-token decode always faster, but throughput inverts at 32B under saturation (-5.15%) alongside -1.8% tok/J; cold-start cost decomposed into capture and torch.compile.

One-shot script to audit GPU, CUDA, PyTorch, CPU, and disk performance before debugging a slow or broken ML environment.

Professional benchmarking guide for evaluating NVIDIA H200 GPU memory bandwidth using the STREAM Triad (FP32) benchmark with CUDA 12.x on Linux. Includes setup, execution, performance analysis, and multi-GPU benchmarking results.

Run a 2-min local benchmark → predict how long your AI job will take on cloud GPU (T4/V100/A100). No guessing, no wasted money.

Ramanujan's mathematics meets the NVIDIA stack: CUDA-Q/cuQuantum quantum simulation + NIM/Nemotron analysis, consumer RTX to cloud H100

Evidence-backed, workload-conditioned autotuning for local LLM inference. Local-first control plane, G0–G8 validation, PyTorch · llama.cpp · vLLM.