Mobious

@anhq-nguyen I was having the same issue. Trying to run the program from the top-right run icon (which is added through the C/C++ extension I believe) would fail with the...

Had the same issue. Apparently there was a blank shortcut at the top of my shortcut list after importing. Deleting that one seemed to fix the problem.

I posted this in #6280 Have you tested this with both streaming and non-streaming requests? I noticed in testing that cancelling requests with `stream=True` causes them to stop running immediately,...

I agree with @finetunej. /abort_request is relatively useless for external clients using the API because: - Requests with `stream=True` are already canceled after the client closes the connection. - When...

If I may suggest an additional requirement: Non-admin user accounts created for use with the frontend UI should be optionally restricted to only to work with certain workspaces. This is...

I found a similar crash also can occur anytime your are running multiple simultaneous requests. In fact this may be the actual source of the problem as I realize that...

@fireblade2534 I just pulled the most recent GPU image ghcr.io/remsky/kokoro-fastapi-gpu:latest, sha256:ce12c3d6f0718d09188f3355b71973cf14c12791b7e17a358fdb9dd3a6faca33 Server still crashed right after running my script, but now prints "free(): invalid pointer" at the end. Here's the...

That test was on Windows. Tested the new image on Ubuntu. Crash still occurs, but was never able to get any error messages from the server. EDIT: Tested the newest...

+1 I'm looking at various RAG solutions right now, and the choice to make you have to run multiple server instances in order to separate workspaces is a very strange...