Shivank Chaudhary·Oct 178x Faster LLM Cold Starts on Kubernetes With NVIDIA Dynamo Snapshot, your guide to scale to 0 and…Testing NVIDIA Dynamo Snapshot on H200s: the numbers, what broke, and where it stops helping.
Shivank Chaudhary·Aug 26From 16 GB/s to 189 GB/s: Debugging a 400G RoCE Fabric for NCCLA systematic walk through everything that can silently throttle GPU collective performance — MTU enums, NUMA topology, PCIe ACS, Kubernetes…
Shivank Chaudhary·Aug 26Deploying a CXI Fabric DRA Driver on Kubernetes: CDI, NRI, ResourceClaims, and Shared VNIs[learning…An end-to-end guide to exposing high-performance HPC NICs to pods with Dynamic Resource Allocation — the concepts, the commands, the actual…
Shivank Chaudhary·Aug 12Serving a Multi-Node LLM on AMD MI300A over HPE Slingshot and Kubernetes [learning resource]Most “deploy an LLM” tutorials assume one box with a handful of NVIDIA GPUs, a CUDA image, and a single docker run. The moment your model…
Shivank Chaudhary·Jun 10Squeezing a 550B Model onto a Single Node: Our Nemotron-3-Ultra Journey on 8× H200We wanted to serve NVIDIA Nemotron-3-Ultra-550B-A55B in production. It’s a beast:
Shivank Chaudhary·Jun 9Running LLMs on AMD MI210 GPUs with vLLM and Kubernetes: A Deployment GuideChat, embedding, and speech models on AMD Instinct MI210 (gfx90a) — with the full manifests and the version/quantization decisions that…A response icon1A response icon1
Shivank Chaudhary·Feb 19Deploying Kimi K2.5 on H200 GPUs: The Real Story Nobody Tells YouI spent the last few days deploying Moonshot AI’s Kimi K2.5 — a 1 trillion parameter Mixture-of-Experts model — on NVIDIA H200 GPUs using…A response icon2A response icon2
Shivank Chaudhary·Dec 9, 2025Benchmarking LLModels with vLLM: A Comprehensive GuideUnderstanding LLM Inference Performance at Scale
Shivank Chaudhary·Nov 1, 2025Deploying a Production-Ready VLLM Stack on Kubernetes with HPA AutoscalingRunning large language models (LLMs) in production requires careful orchestration of resources, efficient scaling mechanisms, and robust…
Shivank Chaudhary·Oct 13, 2025LLM Model FactoryThis blog contains all the yaml files for vllm deployment of various models.