makaveli

Hi, Are you using ```synchronous mode``` ?

I think you need to turn on synchronous_mode: ``` settings = world.get_settings() settings.synchronous_mode = True # Enables synchronous mode settings.fixed_delta_seconds = 0.05 world.apply_settings(settings) ```

Thanks for your quick response @abhi1kumar. - I have used the custom dataset with mmdetection3d and gives expected results. - So, as for the resolution I am using the resolution...

> This is pretty strange. > > > I have used the custom dataset with mmdetection3d and gives expected results. > > Our DEVIANT codebase is essentially a fork of...

@SoftologyPro Okay, to run outside docker a few things: - setup your cuda environment, `cuda 12.3` preferably - And install dependencies by running the `docker/base-image/install-deps.sh` - Next install `tensorrt-llm` by...

Hello @OliverWalter, the docker image mentioned in the readme is actually for 4090 i.e. 89-real. So, you should be able to use: ``` docker run --gpus all --shm-size 64G -p...

@surajwiseyak which gpu are you using? Do you use docker-compose setup?

Not really, because we want to only send one response to the client, at some point we were sending all the responses we add to the `llm_queue` for all updates...

@DamianB-BitFlipper not sure i understand what you mean when you say `sentences`, there are `llm_response` which could be multiple sentences or a single word. > In the current implementation, the...

> I am just postulating, from exploring the code and poking at it, that the transcriber sends: [, ], the way the code is written, the first sentence is lost....