https://fulgurion.com/blog/tags/streaming/Recent content in Streaming on Fulgurion Systems Bloghttps://fulgurion.com/blog/images/Logo-linkedin.pnghttps://fulgurion.com/blog/images/Logo-linkedin.pngHugoen-usThu, 30 Apr 2026 00:00:00 -0300https://fulgurion.com/blog/posts/rust-on-aws-lambda-streaming/Thu, 30 Apr 2026 00:00:00 -0300https://fulgurion.com/blog/posts/rust-on-aws-lambda-streaming/<p>The previous four posts (<a href="https://fulgurion.com/blog/posts/rust-on-aws-lambda/">Part 1</a>, <a href="https://fulgurion.com/blog/posts/rust-on-aws-lambda-cold-start/">Part 2</a>, <a href="https://fulgurion.com/blog/posts/rust-on-aws-lambda-cold-start-anatomy/">Part 3</a>, <a href="https://fulgurion.com/blog/posts/rust-on-aws-lambda-wrong-tool/">Part 4</a>) covered Rust on Lambda from cold starts to architectural fit. This one is a sibling rather than a sequel, focused on a specific AWS gotcha that bites anyone wiring an LLM behind API Gateway: <strong>HTTP API v2 does not support response streaming</strong>. The modern, recommended Gateway flavor is the wrong tool for streaming LLM tokens. The older REST API got streaming support in <strong>November 2025</strong>. If you reach for HTTP API v2 by reflex (and most &ldquo;use the modern one&rdquo; guides will tell you to), your token stream silently collapses into a single buffered response.</p>