Revision History
vLLM · 12 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Added IsoExec architecture, configuration-specific measurements, and reproducibility limits.
Version 12 · Aug 23, 2026, 02:03 AM
- Add Inferact section: maintainers' company launched Jan 22, 2026 with $150M seed led by a16z and Lightspeed; attributed GPU-scale and day-zero-support claims; refs 27-31
Version 11 · Aug 7, 2026, 01:37 PM
- Correction: replace volatile promotional, adoption, funding, release-timeline, and universal benchmark claims with a primary-source account of vLLM's scope, PagedAttention, V1 architecture, interfaces, execution features, deployment, evaluation, security, and limitations; align the platform, preemption, and shared-memory wording with the exact v0.26.0 documentation.
Version 10 · Jul 29, 2026, 06:44 AM
- Added 6 contextual internal links
Version 9 · Jul 23, 2026, 03:04 PM