v0.30.0: [Build] Fix DeepGEMM CUDA 12.9 release builds (#57554)

What moved

Signed-off-by: khluu khluu000@gmail.com Co-authored-by: OpenAI Codex noreply@openai.com Co-authored-by: Jee Jee Li pandaleefree@gmail.com (cherry picked from commit eb87980 ) vLLM issued this as an official post on 2026-09-21. The desk files the title and summary from the allow-listed official source, not a rewrite of claims the source did not make. No second outlet is added, and no launch is invented. The primary source stays on this page so the original wording remains the claim of record.

Why it matters

Signed-off-by: khluu khluu000@gmail.com Co-authored-by: OpenAI Codex noreply@openai.com Co-authored-by: Jee Jee Li pandaleefree@gmail.com (cherry picked from commit eb87980 ) That is a public launch file from vLLM, dated 2026-09-21. Tagged Hardware.

On the record

• Filed from the vLLM official RSS on 2026-09-21.
• Primary source host: github.com.
• The desk does not add a second source.