Revision History
NVIDIA A100 · 10 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 H100 comparison table (H100 sparse rates had been set against A100 dense rates) and the NVLink-doubling claim, removed a false claim that the rackmount DGX A100 lacked MIG, fixed an invalid MIG layout and the L2 compression figures, removed Chinchilla (TPU-trained) from the A100 list, replaced unsupported GPT-4 hardware and Stable Diffusion/Lambda Labs claims, and repointed two wrong references (Microsoft OpenAI supercomputer, CSIS October 2022 export controls) (plus 35 minor fixes)
Version 10 · Nov 2, 2026, 04:46 AM
- Update: added an official video.
Version 9 · Nov 1, 2026, 08:02 AM
- Improve internal links (2026-10-13)
Version 7 · Oct 13, 2026, 10:18 AM
- Added 6 contextual internal links
Version 6 · Jul 23, 2026, 03:28 PM
- Pre-update snapshot before enhancement to 7492 words.
Version 3 · May 18, 2026, 05:11 AM