DeepSeek-V3, R1 671B on 8xH100 Throughput Benchmarks

Z-AI V1.4 发行版本

NVIDIA HPC Benchmarks

Bunch of explanations and tutorials around confidential computing

CLI tool to check Oracle Cloud compute shape availability - find GPU capacity (A100, H100) across regions

In the recent competition, we were challenged to finetune a model that can convert a LaTeX expressions into Python code effectively. My team, which I led, secured 6th place overall.

Patent-pending K8s DaemonSet that validates GPU nodes via GEMM latency, fail-slow CV detection, and NVLink ring profiling before Slurm resumes them

Cog Single GPU Quantized Implementation of Step-Video-T2V

A real-time speech translation web interface that combines Automatic Speech Recognition (ASR) and Neural Machine Translation (NMT) services to provide instant translations in multiple languages. Powered by DigitalOcean GPUs.

Movement Mapper (formerly Matter Activity Logger) is a local-first activity logging and visualization tool designed for smart home motion sensors (specifically Tapo P100/T100 series). It allows you to track, visualize, and analyze movement patterns within your home without relying on cloud dashboards.

LLaMA-Factory FP8 training environment for NVIDIA Hopper GPUs. Fixes common configuration issues causing 2x slowdown with FP8 mixed precision.

Thermal-aware batch controller for vLLM/TensorRT-LLM. Prevents HBM thermal throttling from killing p99 latency on H100/H200. Monitors nvidia-smi, auto-cuts batch size at 85°C, migrates cold KV to DRAM. Prometheus + Grafana included. 4.2s -> 2.1s p99 at 128K context.

Monitor low-utilization time, idle-state episodes, and workload starvation signals on NVIDIA datacenter GPUs.

A drop-in modernization of bowang-lab/scGPT for Python 3.12 + torch 2.6 + flash-attn 3 (H100 sm_90a native). Original pretrained weights load unmodified — compatible, more modern, faster.

Should you buy a DGX Spark or rent H100s? Run on Mac Mini or TAALAS cluster? Full cost & performance comparison of GPU hardware and cloud for Indian AI developers — with data sovereignty, IndiaAI Mission subsidies, and Dynamo 1.0 coverage.

One-offs.

Benchmarking QLC vs TLC NVMe for LLM inference: TPS/TCO comparison of Solidigm D5-P5336 & D7-P5520 on 8×H100 with MiniMax-M2.5

Reference Flash Attention implementation in PyTorch with V1/V2, GQA/MQA, Triton kernels, benchmark and docs.

Production vLLM deployment configs for multi-GPU setups. Docker Compose, pipeline parallelism configs for 2/4/6/8 GPU RTX 6000 Pro, H100, and H200 systems. By Petronella Technology Group.

The Sentinel Engine: A High-Fidelity Forensic Auditor for LLMs. Resolves the Observability Trilemma via Differential Precision Probing (DPP) and ISNI. Discovered the "Deception Horizon" and Magnitude Collapse phenomenon in Llama-3-8B. Achieves 1.00 AUC at 100x lower cost.