Yulong Wang
Yulong Wang
> Hi @fs-eire, thank you very much for the insight! I tried using `Buffer.from(linear_blend_model_uint8_buffer).toString("base64")` to get the `BASE64` string representation of my `Uint8Array` buffer and passed the `BASE64` string into...
@skottmckay @YUNQIUGUO
Is there any chance that we can merge this? JSPI still need to take some time...
I don't know whether there should be a general fix in `testjs`, or `onnxruntime` should submit a fix for compatibility for supporting testjs. Is the tfjs PR mentioned above (https://github.com/tensorflow/tfjs/pull/7181)...
I met similar error before, and #124 fixed this for me. Not sure if it works for you
this may not be the best solution because it duplicates the index.d.ts. However I tried a few ways and this is the only one that works to me.
It has been about 4 months since this PR is out and as you can see we really need this change to be merged and publish to NPM so that...
> Perhaps if the UMD typings are generated by build / excluded from Git, with that one line automatically amended, instead of manually duplicating these? Yes. The recommended way is...
Somehow the codebase owner is unwilling to merge my PR #124. I am currently using the following workaround in my package.json to make typescript happy: ```js "scripts": { ... "preprepare":...
Thanks for the feedback. I think this `env.logLevel` works for onnxruntime-web but not for onnxruntime-node. Need a fix for this.