Blog
AI engineering insights, practical advice, and things I'm learning.
AI Engineering
How to Run TPU Workloads on Google Cloud with Ray 2.55
Learn how to provision Google Cloud TPUs, handle slice topologies, and deploy machine learning models using Ray 2.55 and the KubeRay Operator.
Google Cloud Tpu · Ray Framework · Machine Learning Infrastructure · Kuberay Operator
AI Engineering
How to Scale Diffusers Training With NeMo Automodel
Learn how to fine-tune large diffusion models like FLUX.1-dev and Wan 2.1 across multiple GPUs using the NVIDIA NeMo Automodel library.
Diffusion Models · Gpu Acceleration · Model Fine Tuning
AI Engineering
How to Profile PyTorch Attention Kernels on A100 GPUs
Learn how to use the PyTorch profiler to identify memory and compute bottlenecks in attention mechanisms using Hugging Face's tracing methodology.
Pytorch Profiler · Attention Mechanism · Gpu Optimization
AI Engineering
How to Cut CPU Costs with Cloudflare Workers Cache
You will learn how to configure Cloudflare Workers Cache to serve responses directly from entrypoints, handle invalidations, and partition cache keys.
Cloudflare Workers · Edge Computing · Serverless Optimization
AI Engineering
How to launch Hugging Face models in SageMaker Studio
You will learn how to use the new Hugging Face integration to automatically provision and deploy open-source models directly into Amazon SageMaker Studio.
Hugging Face · Amazon Sagemaker · Model Deployment
AI Engineering
SkyPilot Drops Cross-Cloud Egress Fees With Hugging Face Storage
Configure SkyPilot to mount Hugging Face Storage natively and eliminate cross-cloud egress fees for multi-cloud AI workloads.
Multi Cloud · Skypilot · Hugging Face
AI Engineering
How to Configure Elastic Training in MaxText on TPUs
Learn how to enable elastic training in MaxText to survive hardware failures and resume distributed AI workloads in seconds.
Tpu Acceleration · Distributed Training · Fault Tolerance
AI Engineering
How to Expose Ephemeral vLLM Endpoints on Hugging Face Jobs
Learn how to spin up temporary, OpenAI-compatible vLLM inference endpoints on Hugging Face serverless infrastructure using a single CLI command.
Vllm · Hugging Face · Serverless Inference
AI Engineering
How to Implement Saga Rollbacks in Cloudflare Workflows
Learn how to manage distributed transactions and write compensating actions using the saga rollback feature in Cloudflare Workflows.
Distributed Transactions · Cloudflare Workflows · State Management
AI Engineering
How to Speed Up MoE Fine-Tuning With NeMo AutoModel
Learn how to configure NVIDIA NeMo AutoModel in Transformers v5 to increase MoE training throughput and reduce GPU memory usage.
Mixture Of Experts · Nvidia Nemo · Model Fine Tuning
AI Engineering
How to Secure Claude API Workloads With Identity Federation
You will learn how to configure Workload Identity Federation to authenticate non-human Claude API requests and eliminate static access keys.
Claude Api · Workload Identity Federation · Cloud Security
AI Engineering
How to Configure Sparse-LoRA and DoRA With Hugging Face PEFT
Learn how to use PEFT 0.18.0 to configure Sparse-LoRA, DoRA, LoRA-XS, and rsLoRA for more efficient fine-tuning on single-GPU hardware.
Parameter Efficient Fine Tuning · Hugging Face Peft · Large Language Models
AI Engineering
How to Run In-Loop Model Evaluations With olmo-eval
Learn how to set up olmo-eval to test large language model checkpoints during the training process using vLLM, LiteLLM, and Docker-based agent sandboxes.
Llm Evaluation · Model Training · Vllm
AI Engineering
How to Fuse PyTorch MLP Kernels for a 30% Inference Speedup
Learn how to analyze PyTorch profiler traces and implement Liger kernel fusion to significantly reduce memory bandwidth bottlenecks in transformer models.
Pytorch · Kernel Fusion · Inference Optimization
AI Engineering
How to Serve DiffusionGemma Locally With vLLM
Learn how to deploy Google's 26B text diffusion model on local hardware to achieve massive parallel generation speeds using vLLM and Hugging Face.
Diffusion Models · Local Deployment · Vllm Inference
AI Engineering
How to Route GPU GitHub Actions to Hugging Face Jobs
Offload your training and GPU-heavy CI workloads to Hugging Face Jobs using their new ephemeral GitHub runners and action integrations.
Github Actions · Hugging Face · Gpu Computing
AI Engineering
How to Call Claude 4.5 via Apple Foundation Models Framework
Learn how to integrate Claude 4.5 into your Swift applications using Apple's new Foundation Models framework for hybrid on-device and cloud processing.
Claude 4 5 · Apple Foundation Models · Swift Programming
AI Engineering
How to Provision Google Colab GPUs From the Command Line
Learn how to install the Google Colab CLI, provision high-performance remote GPUs from your local terminal, and execute headless machine learning workflows.
Google Colab · Gpu Provisioning · Command Line Interface
AI Engineering
How to Stop OCR Degeneration With DharmaOCR Lite 3B
Dharma-AI's new DharmaOCR models apply DPO to eliminate autoregressive looping. Learn how to configure the 3B parameter model for structured JSON extraction.
Optical Character Recognition · Direct Preference Optimization · Structured Data Extraction
AI Engineering
How to Find GPU Gaps in PyTorch 2.12 With torch.profiler
Learn how to identify performance bottlenecks and idle GPU lanes using the native torch.profiler in PyTorch 2.12 across Blackwell and AMD hardware.
Pytorch · Gpu Optimization · Performance Profiling