docs(ai-stack): disambiguate Tesla brand name from Tesla microarchitecture

"Tesla" was NVIDIA's datacenter-card brand (retired after Volta), spanning
four unrelated architecture generations (Kepler/Maxwell/Pascal/Volta) - a
different, much older thing than the Tesla microarchitecture itself, which
actually predates Fermi/Kepler/Maxwell/Pascal/Volta. Clarify to avoid
reading the power-connector note as claiming Tesla == Volta.
This commit is contained in:
Claude
2026-08-22 03:55:27 +00:00
parent 7f23860078
commit c703b1c4b4
+7 -2
View File
@@ -97,8 +97,13 @@ driver and `nvidia-container-toolkit` are still on you to install first,
and getting the driver branch right is what actually matters here, not the and getting the driver branch right is what actually matters here, not the
Ubuntu version itself. Ubuntu version itself.
**Tesla-card power connector — don't assume standard PCIe.** V100/P100/P40/M40 **"Tesla"-branded card power connector — don't assume standard PCIe.**
PCIe cards take an 8-pin **CPU/EPS12V** connector, not the 6+2-pin PCIe ("Tesla" here is NVIDIA's old datacenter-card *brand name*, retired after
Volta — not the unrelated, much older Tesla *microarchitecture* that
predates Fermi/Kepler/Maxwell/Pascal/Volta. V100/P100/P40/M40 all shipped
under the Tesla brand despite being four different architecture
generations.) These PCIe cards take an 8-pin **CPU/EPS12V** connector, not
the 6+2-pin PCIe
connector a normal GPU uses — a standard PCIe cable will not plug in. Get the connector a normal GPU uses — a standard PCIe cable will not plug in. Get the
dongle/adapter (splits a PCIe 8-pin into EPS12V, or use a real EPS cable) and dongle/adapter (splits a PCIe 8-pin into EPS12V, or use a real EPS cable) and
never daisy-chain both 8-pin rails off one PSU cable/splitter — use two never daisy-chain both 8-pin rails off one PSU cable/splitter — use two