sagemaker
PulseAugur coverage of sagemaker — every cluster mentioning sagemaker across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
MLOps: Migrating ML Inference from SageMaker to Snowflake
This article discusses the benefits of migrating machine learning inference workloads from Amazon SageMaker to Snowflake. The author advocates for moving models to where the data resides within Snowflake, rather than co…
-
MLOps Explained: Bridging the Gap from Notebook to Production · 8 sources tracked
This cluster of articles explores MLOps, the practice of applying DevOps principles to machine learning models to ensure they can be reliably deployed and maintained in production. Several pieces detail how to build sel…
-
Qdrant cuts RAG token costs by 67% with native ColBERT reranking
Qdrant has introduced a native ColBERT reranking feature that significantly reduces token costs for Retrieval-Augmented Generation (RAG) systems. This new capability allows Qdrant to perform token-to-token comparisons d…
-
Amazon to retire Mechanical Turk, ending new customer sign-ups
Amazon is phasing out its Mechanical Turk crowdsourcing service by stopping new customer sign-ups on July 30, 2026. While existing users can continue to access the platform, Amazon has stated it does not plan to introdu…
-
LINE MAN Wongnai cuts AI server costs 9x, boosts app speed 4x
LINE MAN Wongnai has significantly reduced its AI server costs by 9 times and improved application speed by 4 times. This was achieved through a strategic shift in their MLOps approach, optimizing resource utilization a…
-
Bank Risk Intelligence Engine Relies on MLOps and Data Analytics Tools
This article details the daily tasks of a Risk Data Analytics professional within a modern bank, focusing on the MLOps pipeline. The role involves utilizing tools like Python, SQL, and Jupyter Notebooks to manage and an…
-
Cisco AI launches FAPO for automated LLM pipeline optimization
Cisco AI has developed FAPO, an open-source system designed to autonomously optimize multi-step LLM pipelines. FAPO uses Claude Code to evaluate, classify failures, propose variants, and iterate on prompts to achieve ta…
-
Deploying a 35B MoE Model to SageMaker Cost-Effectively
This article details the process of deploying a fine-tuned 35B Mixture-of-Experts (MoE) model to Amazon SageMaker. It focuses on practical strategies for cost-effective deployment, specifically using QLoRA fine-tuning f…
-
Fine-tuning mBART-50 with LoRA on SageMaker matches GPT-4
A technical article details how to fine-tune the mBART-50 model using LoRA on Amazon SageMaker. The process aims to achieve performance comparable to GPT-4 for translation tasks. The method involves a two-step approach:…
-
FlightSense platform predicts flight delays using AI and propagation features
Researchers have developed FlightSense, an MLOps platform designed to predict flight delays by modeling how delays propagate through aircraft rotation chains. The system achieved an AUC of 0.879 by incorporating delay p…
-
Neura Robotics and AWS partner to deploy physical AI in real-world settings
German robotics company Neura Robotics has partnered with AWS to accelerate the deployment of physical AI. The collaboration will see AWS become Neura's primary cloud provider, hosting its Neuraverse platform for traini…
-
Mechanisms for Effective Technical Teams
Eugene Yan's article outlines several mechanisms to enhance the productivity and effectiveness of technical teams, particularly those involved in machine learning. Key practices include End-of-Week Debriefs (EOWDs) for …
-
Data scientists can influence without authority using data and Socratic questioning
Eugene Yan's article offers strategies for data scientists to influence decisions without formal authority, emphasizing the use of data and the Socratic method. He suggests leveraging quantitative and qualitative data t…
-
Eugene Yan reflects on Amazon role and prolific writing in 2020
Eugene Yan's 2020 retrospective details his move to Seattle for a new role at Amazon, where he builds recommender and machine learning systems. He emphasizes learning to scale himself through documentation, system desig…
-
ML research advances, system design patterns, and strategic problem selection explored
Eugene Yan's series of articles explores practical aspects of applying machine learning in real-world systems. He emphasizes starting projects with heuristics before implementing ML, the importance of design patterns fo…