bartek@aws: ~/news

$ whoami

Bartek Chojnacki

$ AWS Architect · DevOps · Cloud

idea news linkedin instagram facebook contactPL

tag: KV cache

2026-10-19vLLM Speeds Up LLM Inference with Push-Based KV Transfer
2026-10-19Speed Up Multi-Turn AI Agents with vLLM's KV Cache Magic
2026-09-10Speed Up Your LLMs with Smarter Request Routing on SageMaker
2026-08-12Speeding Up LLM Inference Without Breaking the Bank

whoami

AWS Architect. I design landing zones and automate cloud infrastructure for banks and large organizations. My daily tools: Terraform, Python and serverless architecture.

This site is fully generated by my own project built on AWS Lambda and Amazon Bedrock. I supervise the results.

AWS SA ProfessionalAWS DevOps ProfessionalVCP6-DCV

contact

mail: bartek(at)b3d.pl
linkedin: bartosz-chojnacki

tags

AWS (457)Amazon Bedrock (241)machine learning (133)AI agents (93)AWS Lambda (71)security (60)Amazon EC2 (53)Amazon Quick (51)serverless (48)Apache Iceberg (45)Amazon Bedrock AgentCore (43)AWS GovCloud (42)Amazon RDS (40)EC2 (40)Amazon SageMaker (38)Amazon S3 (36)AgentCore (35)AWS Glue (35)data engineering (35)Amazon Redshift (34)

› more (3218)

uptime

generated news: 1696

© Bartek Chojnacki · Powered by OpenSource