Repository Issue Activity (beta)

#164 Podman support

#168 Cant start run.sh "unknown shorthand flag: 'f' in -f"

#129 Unable to build CUDA-enabled image, missing Makefile

#23 [Feature Request] is possible to add a password or a login screen before we can acess the chat ?

#163 cude issue : cant get this to work ./run.sh --model 7b --with-cuda

#151 Can't run on Linux

#5 Crashes on long message - Internal Server Error.

#162 Some Python related errors resulting in "Host [llama-gpt-api:8000] not yet available..." and exit code of 1

#132 nvidia-container-cli error

#155 llama 3 support

#86 Stuck on '[Host [llama-gpt-api-cuda-ggml:8000] not yet available...'

#89 Support file upload

#161 Intel CPU support

#157 [FEATURE REQUEST] Support for NPU hardware acceleration

#160 models download

#159 coroutine error StopIteration if the AI response is empty

#158 Unable to increase max token size

#35 How to use my own models?

#121 Error when running model other than 7b

#154 Add API Key restriction so the API is not always OPEN

#148 Is there the ability to swap the language to answer?

#116 Please add Intel A770 support

#146 Not enough space

#153 Error when deploying in Kubernetes: Model path does not exist

#152 Way to change model on UmbrelOS