-
I am working on an app where I want make multiple parallel requests to a server. As some of these request require time for processing the client waits for multiple replies in parallel. In this situati…
-
I originally posted my issue on the Streamlit Authenticator project ([here](https://github.com/mkhorasani/Streamlit-Authenticator/issues/99#issuecomment-1823313157) but the problem seems to be with th…
-
Tried tensorflow and torch with tinygrad
still getting this error with llama 8b 3.1 and llama 8b as well.
Apparently this is an opencl compile error for bfloat16 data type
Sorry, I am not a kernel …
-
I have copy the json from the extension as per the instruction but it still not working
 in x86 Linux/Ubuntu, I installed latest exo . It can't work with LLVM backend. With below command.
DEBUG=9 LLVM=1 exo run llama-3.1-8b --prompt "hello, who are you?" --…
-
Thanks for the update - excited to try streaming.
Neither .stream nor .chat are working for me since the last update though:
> conversation.chat(query)
Traceback (most recent call last):
Fil…
-
I am not sure how chat is being stored at the moment, but I think the ability to export chat is always a useful feature. As a bare minimum, it would be nice to be able to get a copy-and-pasteable JSON…