Pierrick Hymbert
Pierrick Hymbert
@TheBongStack reading the issue again, I think it is easier to pass the token until loadmodel_from_url and add it as Authorization Bearer header.
Hi @TheBongStack, are you still working on this issue ?
No worries, take your time. You need to concatenate `hf_token` in the url just where the `hf_repo` is used: https://github.com/ggerganov/llama.cpp/blob/master/common/common.cpp#L2183 The token must be before the hostname prefixed with an...
I yes I got it, a token cannot be passed as a `user:password@host` in curl url. Then modify the `load_model_from_url` to take a token as parameter
It has been addressed the xz weekend here: - #6409 But I am happy that finally the code is removed, so looks good
> Re/ Windows, I realize I've assumed people build from within WSL (or cross-build from Linux), but would need confirmation. We cannot assume unfortunately, I have the feeling most windows...
Agreed, I am doing performance and capacity tests since 2 month+, there is no such bug. The server is stable and production ready.
Yeah, it is identified in: - #6421
> Before we make the change, we should see if the `update_slots` error is really reproducible. We can conclude that the user was using an old version. That's it.