🚀 MLOps - hello · Scour

avinashmnth2507-dev/mlops-house-price-predictor: Production-grade MLOps pipeline for house price prediction 🦙Ollama

github.com·7h·DEV

Data Annotation Infrastructure: Building a Scalable Pipeline with CVAT and B2 Object Storage 🌀Naiad

backblaze.com·4d

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling ⚡Incremental Computation

How to Eliminate Pipeline Friction in AI Model Serving 🌀Naiad

developer.nvidia.com·3h

How ML Systems Actually Work: From Data to Deployment 📱Edge AI

newsletter.systemdesign.one

·12h

ML Pipelines for Data Scientists: A Beginner’s Guide to Automating Everything Between Raw Data and… 📊Data Science

·3d

Blog | Owning your model deployment 🕵️Jaeger

nchagnet.eu·9h

What Actually Happens to an AI Model After Deploy 🎲Deterministic Simulation

siliconopera.com·3d

Local models, inference incantations and pi extensions 🦙Ollama

gurupanguji.com·3d

On-Device Machine Learning 🦙Ollama

dsebastien.net·6d

Zero Chaos: Scaling Detection Engineering at the Speed of Software, with Detection As Code 🏗️Cranelift

vLLM V0 to V1: Correctness Before Corrections in RL 📊Profile-Guided Optimization

huggingface.co·6d

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox 💬Prompt Engineering

Using MemAlign to Improve Evaluation of Traditional Machine Learning in Genie Code 🔍KLEE

databricks.com·4d

DataMaster: Towards Autonomous Data Engineering for Machine Learning 🧮Vector Databases

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation 📱Edge AI

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning 🤖TVM

Why Retrying Fails: Context Contamination in LLM Agent Pipelines 💬Prompt Engineering

RepoZero: Can LLMs Generate a Code Repository from Scratch? 🏗️Cranelift

Switchcraft: AI Model Router for Agentic Tool Calling 🦙Ollama

Log in to enable infinite scrolling