Submissions by covi

Large-Scale AI Batch Inference: 9x Faster Embedding Generation

Abusing SQLite to Handle Concurrency

Using DeepSeek R1 for RAG: Do's and Don'ts

Building Large-Scale Image Search Using VectorDB and OpenAI Clip

Fungible cloud compute and storage: AI training on any cloud

Getting $1M cloud credits for AI startups – and using them wisely

You Ran the Operational Database on What? Testing Spot Instances

Can Multi-Modal LLMs "See" Images? A Deep Dive with ASCII Art

Embarrassingly parallel batch jobs on multiple clouds or regions

Llama 3.1 finetuning on your own data and infra, without vendor lock-in

Guide: Finetune Llama 3.1 on your infra

AI on Kubernetes Without the Pain

Dagster and SkyPilot: Orchestrating LLM training cost-effectively

Inflection CEO Left, Became CEO of Microsoft AI

SkyServe: A cost-efficient, multi-region/cloud library for serving GenAI models

SGLang: Fast and Expressive LLM Inference with RadixAttention for 5x Throughput

SkyServe: 50% Cheaper AI Serving on Any Cloud with High Availability

Tigris: Globally Distributed S3-Compatible Object Storage

Scaling Mixtral LLM Serving Across Clouds

Covariant: Moving from on-prem to the cloud for 4x faster AI development

ML experiments in the cloud with SkyPilot and DVC