Dominik Weckmüller

## UI > your current scenario makes your UI render the dropdown conditionally based on if the 'quantize embedding' is set to true eg Exactly. One dropdown with all 3...

@cv-or could you run your problem instance one time with v1.8 (if possible feature-wise)? In my personal experience, v1.8 delivers more consistent (good, but not perfectly consistent) results (e.g. when...

### Results: v1.8 vs v1.14 unassigned jobs @jcoupey I finally managed to test quite some real-world instances with roughly 40 - 60 jobs and identify a dozen comparison cases. **Result:...

Yes, the distances can be safely removed and have no importance in these instances. I can share some coordinates but prefer to send these via email.

This is really cool and paves the way for LLMs running in the browser! I had this idea in my head for a while now: we already have a kind...

Sounds great!  It's also on the feature/idea list of the `readme.md` that this repo could become a browser plugin for FF or Chrome. Of course, it would need a leaner...

We're finally getting closer to WebGPU support: https://github.com/xenova/transformers.js/pull/545 It's already usable in the dev branch. I'm really excited about this as people are reporting accelerations of factor 20x-100x! In my...

### Transformers.js and WebGPU Folks, it's finally here 🥹 https://huggingface.co/posts/Xenova/681836693682285 However, afaik there is no docs for v3 yet. I tried updating SemanticFinder with v3 and running some quick tests,...

@gdmcdonald thanks for the references. Note that in these examples, they used the "old" packages from `@Xenova/transformers`, here I tried with the new `@huggingface/transformers` On my screenshot above you can...

Found a bug with webgpu (wasm works fine): https://github.com/xenova/transformers.js/issues/909 The problem is calling the extractor two consecutive times. The first time works (for the query embedding) but the second time...