Skip to content

docs: README — add NVIDIA GB10 (CUDA) support - #36

Merged
prabod merged 1 commit into
mainfrom
docs/readme-v0.2.0
Jul 31, 2026
Merged

docs: README — add NVIDIA GB10 (CUDA) support#36
prabod merged 1 commit into
mainfrom
docs/readme-v0.2.0

Conversation

@prabod

@prabod prabod commented Jul 31, 2026

Copy link
Copy Markdown
Contributor

BaseRT now runs on Apple Silicon (Metal) and NVIDIA GB10 / DGX Spark (CUDA). Minimal update:

  • Tagline: Fastest LLM inference on Apple Silicon — now on NVIDIA GB10 (DGX Spark), too. (keeps the Apple-Silicon "fastest" claim; no performance claim on NVIDIA)
  • Platform badge → Apple Silicon · NVIDIA GB10
  • Intro + Requirements note both backends
  • One-line install tweak ("prebuilt engine for your platform")

No verbose design commentary; everything else unchanged. Pairs with the 0.2.0 release (#33 install.sh, #34 catalog, #35 changelog).

BaseRT now runs on Apple Silicon (Metal) and NVIDIA GB10 / DGX Spark (CUDA).
Update the tagline (fastest on Apple Silicon; no performance claim on NVIDIA),
platform badge, intro, and requirements.
@prabod
prabod merged commit 09c34e4 into main Jul 31, 2026
10 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant