Victor Nogueira
Victor Nogueira
It's related to the `RequestError [HttpError]: Resource not accessible by integration`, which can happen if those permissions are not set. For example, this error can occur if a person creating...
That's true, it's up to the user. My suggestion was to point the users to this info somewhere in the Readme, because I assume more users will open [issues related...
Alright! Then I plan to do a PR soon. [If anyone else reading this wants to do it earlier, feel free to use/adapt the function I shared above!]
Oh yeah! I've faced this problem too!
> read the file chunk by chunk (so it uses less RAM) > > In theory, we could do the same with a remote file (i.e. loadModelFromUrl) Would love to...
That's great news!! You've done a lot and Wllama is in great shape! Take your time and all the best with the career move!
Just tested it! And it's all working fine, except for one thing: It's not caching the models anymore on iOS browsers (tested with Mobile Safari and Mobile Brave) On both,...
Excellent 🙌 On iOS, it's now loading from the cache correctly!
Thanks for the reference. There is a lot of good info in that thread! I've just noticed a pattern regarding this issue: The `loadModelFromUrl` function is only hanging when running...
ℹ️ This issue (`loadModelFromUrl` hanging when used with multi-threading and loading a too-large model) is still present in v1.9.0. I tried adjusting the `stepBytes` and `maxBytes` from `getWasmMemory()` to see...