You are viewing a plain text version of this content. The canonical link for it is here.
Posted to discuss-archive@tvm.apache.org by "akaashrp (via GitHub)" <gi...@apache.org> on 2026/01/22 21:39:43 UTC
[PR] [Web][Version] Fix WebLLM vision model issues [tvm]
akaashrp opened a new pull request, #18680:
URL: https://github.com/apache/tvm/pull/18680
1. Rename FTVMFFIErrorSetRaisedFromCStr to TVMFFIErrorSetRaisedFromCStr
2. Try multiple candidates for maxComputeInvocationsPerWorkgroup
3. Update tvmjs version to 0.23.0-dev2
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For additional commands, e-mail: discuss-archive-help@tvm.apache.org
Re: [PR] [Web][Version] Fix WebLLM vision model issues [tvm]
Posted by "gemini-code-assist[bot] (via GitHub)" <gi...@apache.org>.
gemini-code-assist[bot] commented on PR #18680:
URL: https://github.com/apache/tvm/pull/18680#issuecomment-3786824307
## Summary of Changes
Hello @akaashrp, I'm Gemini Code Assist[^1]! 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](https://codeassist.google/code-review/login) to enable Memory in your admin console.**
<details>
<summary><b>Using Gemini Code Assist</b></summary>
<br>
The full guide for Gemini Code Assist can be found on our [documentation page](https://developers.google.com/gemini-code-assist/docs/review-github-code), here are some quick tips.
<b>Invoking Gemini</b>
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.
<b>Customization</b>
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](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github).
<b>Limitations & Feedback</b>
Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with :thumbsup: and :thumbsdown: 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](https://google.qualtrics.com/jfe/form/SV_2cyuGuTWsEw84yG).
<b>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](https://cloud.google.com/products/gemini/code-assist).</b>
</details>
[^1]: Review the [Privacy Notices](https://policies.google.com/privacy), [Generative AI Prohibited Use Policy](https://policies.google.com/terms/generative-ai/use-policy), [Terms of Service](https://policies.google.com/terms), and learn how to configure Gemini Code Assist in GitHub [here](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github). Gemini can make mistakes, so double check it and [use code with caution](https://support.google.com/legal/answer/13505487).
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For additional commands, e-mail: discuss-archive-help@tvm.apache.org
Re: [PR] [Web][Version] Fix WebLLM vision model issues [tvm]
Posted by "gemini-code-assist[bot] (via GitHub)" <gi...@apache.org>.
gemini-code-assist[bot] commented on code in PR #18680:
URL: https://github.com/apache/tvm/pull/18680#discussion_r2718741000
##########
web/src/webgpu.ts:
##########
@@ -110,6 +110,18 @@ export async function detectGPUDevice(powerPreference: "low-power" | "high-perfo
);
}
+ const candidates = [1024, 512, 256];
+ const limit = adapter.limits.maxComputeInvocationsPerWorkgroup;
+ const requiredMaxComputeInvocationsPerWorkgroup = candidates.find(x => x <= limit) || undefined;
Review Comment:

The `|| undefined` is redundant here. `Array.prototype.find()` already returns `undefined` if no element satisfies the testing function.
```suggestion
const requiredMaxComputeInvocationsPerWorkgroup = candidates.find(x => x <= limit);
```
##########
web/src/runtime.ts:
##########
@@ -2146,7 +2146,7 @@ export class Instance implements Disposable {
const errMsgOffset = stack.allocRawBytes(errMsg.length + 1);
stack.storeRawBytes(errMsgOffset, StringToUint8Array(errMsg));
stack.commitToWasmMemory();
- (this.lib.exports.FTVMFFIErrorSetRaisedFromCStr as ctypes.FTVMFFIErrorSetRaisedFromCStr)(
+ (this.lib.exports.TVMFFIErrorSetRaisedFromCStr as ctypes.FTVMFFIErrorSetRaisedFromCStr)(
stack.ptrFromOffset(errKindOffset),
stack.ptrFromOffset(errMsgOffset)
);
Review Comment:

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.
```suggestion
(this.lib.exports.TVMFFIErrorSetRaisedFromCStr as ctypes.TVMFFIErrorSetRaisedFromCStr)(
stack.ptrFromOffset(errKindOffset),
stack.ptrFromOffset(errMsgOffset)
);
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For additional commands, e-mail: discuss-archive-help@tvm.apache.org
Re: [PR] [Web][Version] Fix WebLLM vision model issues [tvm]
Posted by "tqchen (via GitHub)" <gi...@apache.org>.
tqchen merged PR #18680:
URL: https://github.com/apache/tvm/pull/18680
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For additional commands, e-mail: discuss-archive-help@tvm.apache.org
Re: [PR] [Web][Version] Fix WebLLM vision model issues [tvm]
Posted by "tqchen (via GitHub)" <gi...@apache.org>.
tqchen commented on PR #18680:
URL: https://github.com/apache/tvm/pull/18680#issuecomment-3805243503
@akaashrp we need a rebase
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: discuss-archive-unsubscribe@tvm.apache.org
For additional commands, e-mail: discuss-archive-help@tvm.apache.org