Skip to content

Update comments in getting-started.md for clarity #202

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
justinchuby merged 1 commit into from
Apr 23, 2026
Merged

Update comments in getting-started.md for clarity #202

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/getting-started.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -218,7 +218,7 @@ It drives the entire build pipeline — graph construction, operator fusion,
dead input removal, and KV cache sizing are all tailored for the target EP:

```bash
# Default (portable ONNX with standard fusions, no vendor-specific ops)
# Default (portable ONNX with standard fusions as model local functions)

Copilot AI Apr 23, 2026

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The “Default” description here is potentially misleading: the default EP still applies fusions by emitting custom-domain ops (e.g., com.microsoft Skip* ops) with ONNX function bodies as a portable fallback. Consider rephrasing to explicitly mention “custom ops with ONNX function bodies/local functions” (or similar) so readers don’t interpret this as purely standard-ONNX nodes only.

Suggested change
# Default (portable ONNX with standard fusions as model local functions)
# Default (portable ONNX using custom fused ops with ONNX function bodies/local functions)

Copilot uses AI. Check for mistakes.
mobius build --model meta-llama/Llama-3.2-1B output/

# CPU (GQA fusion for f32)
Expand All @@ -236,7 +236,7 @@ mobius build --model meta-llama/Llama-3.2-1B output/ --ep trt-rtx --dtype f16
# WebGPU
mobius build --model meta-llama/Llama-3.2-1B output/ --ep webgpu --dtype f16

# Strict ONNX standard (zero custom ops, runs on any ONNX runtime)
# Strict ONNX standard (zero custom ops)

Copilot AI Apr 23, 2026

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This “onnx-standard” description drops the key user-facing implication that the output should run on any conformant ONNX runtime without ORT extensions (matching the behavior described in src/mobius/_execution_providers.py). Consider adding that qualifier back (instead of just “zero custom ops”) to keep the guidance actionable.

Suggested change
# Strict ONNX standard (zero custom ops)
# Strict ONNX standard (runs on conformant ONNX runtimes without ORT
# extensions; zero custom ops)

Copilot uses AI. Check for mistakes.
mobius build --model meta-llama/Llama-3.2-1B output/ --ep onnx-standard
```

Expand Down
Loading