Revision History
AMD Instinct MI300X · 9 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.
- Correction: Corrected the MI300X article's misattributed 146-billion transistor figure (it is the MI300A's), xGMI link bandwidth, a fabricated '57 percent' latency figure and other misreported ChipsAndCheese and SemiAnalysis results including a non-verbatim quote, the NVIDIA rebuttal chronology, AMD's Llama 2 and MI325X benchmark claims, DeepSeek-R1 concurrency, El Capitan's APU count, node layout and Linpack figure (and its June 2026 loss of the No. 1 spot), revenue figures that mixed segment and GPU totals, swapped MI350X/MI355X specs, and a fabricated TensorOpera row (plus 39 minor fixes)
Version 9 · Nov 2, 2026, 01:38 PM
- Improve internal links (2026-10-13)
Version 7 · Oct 13, 2026, 10:21 AM
- Added 6 contextual internal links
Version 5 · Jul 23, 2026, 03:30 PM