[Web][Version] Fix WebLLM vision model issues

[akaashrp]

1. Rename FTVMFFIErrorSetRaisedFromCStr to TVMFFIErrorSetRaisedFromCStr
2. Try multiple candidates for maxComputeInvocationsPerWorkgroup
3. Update tvmjs version to 0.23.0-dev2

[gemini-code-assist]

Summary of Changes

Hello @akaashrp, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request aims to resolve issues impacting WebLLM vision models by performing a version bump for the tvmjs package, rectifying a naming inconsistency in an FFI error function, and enhancing WebGPU device compatibility. The most significant change involves a more adaptive approach to configuring WebGPU's compute capabilities, ensuring that the maxComputeInvocationsPerWorkgroup setting is optimized for the specific hardware's limitations.

Highlights

• Version Update: The tvmjs package version has been updated from 0.23.0-dev1 to 0.23.0-dev2.
• FFI Function Rename: A typo in the FFI error handling function FTVMFFIErrorSetRaisedFromCStr has been corrected to TVMFFIErrorSetRaisedFromCStr.
• WebGPU Compute Invocation Handling: Logic has been added to dynamically select an appropriate maxComputeInvocationsPerWorkgroup for WebGPU adapters, trying candidates like 1024, 512, and 256 based on device limits to improve compatibility.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces fixes for WebLLM vision models, including updating the package version, renaming an FFI function, and adding logic to dynamically select maxComputeInvocationsPerWorkgroup based on device limits. The changes are generally good, but I've found a couple of areas for improvement. Specifically, there's an incomplete refactoring where a function rename was not propagated to its type cast, which could lead to build or runtime errors. I've also pointed out a small code redundancy that can be simplified. Please see the detailed comments.

[gemini-code-assist]

The function name has been updated to TVMFFIErrorSetRaisedFromCStr, but it's being cast to the old type ctypes.FTVMFFIErrorSetRaisedFromCStr. This is inconsistent and suggests an incomplete refactoring. The type definition in ctypes.ts and this cast should be updated to use the new name TVMFFIErrorSetRaisedFromCStr for consistency.

Suggested change

	(this.lib.exports.TVMFFIErrorSetRaisedFromCStr as ctypes.FTVMFFIErrorSetRaisedFromCStr)(
	stack.ptrFromOffset(errKindOffset),
	stack.ptrFromOffset(errMsgOffset)
	);
	(this.lib.exports.TVMFFIErrorSetRaisedFromCStr as ctypes.TVMFFIErrorSetRaisedFromCStr)(
	stack.ptrFromOffset(errKindOffset),
	stack.ptrFromOffset(errMsgOffset)
	);

[gemini-code-assist]

The || undefined is redundant here. Array.prototype.find() already returns undefined if no element satisfies the testing function.

Suggested change

	const requiredMaxComputeInvocationsPerWorkgroup = candidates.find(x => x <= limit) || undefined;
	const requiredMaxComputeInvocationsPerWorkgroup = candidates.find(x => x <= limit);

[tqchen]

@akaashrp we need a rebase