Welcome to the Daft blog
Join us as we explore innovative ways to handle multimodal datasets, optimize performance, and revolutionize your data workflows.
Engineering
November 4, 2025
Cutting LLM Batch Inference Time in Half: Dynamic Prefix Bucketing at Scale
A new inference backend that maximizes batch inference throughput.
Engineering
October 1, 2025
Benchmarks for Multimodal AI Workloads
Spark, Ray Data, and Daft
Announcements
Engineering
October 1, 2025
Introducing Flotilla: Simplifying Multimodal Data Processing at Scale
Daft's new distributed engine
Engineering
September 30, 2025
Exploring Daft's Local Execution
The Swordfish Engine
Engineering
September 24, 2025
After the First Run
Using Daft’s observability tools to uncover performance pitfalls
Engineering
September 10, 2025
Making GPUs Zoom (Part 1)
A deep dive into GPU optimizations for production-scale multimodal data processing
Engineering
September 3, 2025
End-to-End Distributed PDF Processing Pipeline
OCR, Spatial Analysis & GPU Embeddings with Python
Engineering
August 26, 2025
How to Build Scalable, End-to-end Batch Inference Pipelines with Daft
From prompts to parquet: making batch inference simple, fast, and scalable.
Engineering
Video
August 13, 2025
Embedding Millions of Text Documents With Qwen3
Near-100% GPU Utilization
Engineering
August 6, 2025
Processing 300K Images Without OOM
A Streaming Solution
Engineering
April 22, 2025
We cloned over 15,000 repos to find the best developers
An adventure in AI and data engineering to analyze developers across Github
Engineering
March 18, 2025
DeepSeek smallpond, 3FS and data processing for AI
A closer look beyond the AI hype
PreviousPage 1 of 2
