Issues
- 0
Intel CPU support
#161 opened by rivailruiz - 0
- 0
models download
#160 opened by room3622 - 0
- 0
Unable to increase max token size
#158 opened by Usgupta - 3
llama 3 support
#155 opened by gyzerok - 8
Error when running model other than 7b
#121 opened by Impre-visible - 0
- 0
Is there the ability to swap the language to answer?
#148 opened by n0raitor - 1
Please add Intel A770 support
#116 opened by johnuopini - 1
Llama GPT extremely slow on Umbrel Home
#149 opened by anthony-robin - 3
Can't use GPU: could not select device driver "nvidia" with capabilities: [[gpu]]
#150 opened by ProgrammingLife - 1
Not enough space
#146 opened by gruzilla - 0
- 1
IPv6 support
#145 opened by JuniperChris929 - 1
Way to change model on UmbrelOS
#152 opened by lilxanman - 1
Can't run on Linux
#151 opened by ProgrammingLife - 2
Errors thrown when trying to start llama-gpt api using docker-compose-gguf.yml
#144 opened by ghevge - 2
- 0
Support Multi-part .bin files?
#147 opened by AI-Zebra - 0
CUDA Support for Kubernetes
#143 opened by AndreasMurk - 2
nvidia-container-cli error
#132 opened by bankersbaddream - 1
Are there any plans for load custom models?
#136 opened by classfang - 2
docker compose: Permission denied running /api/run.sh
#142 opened by roblem - 0
Installation on windows - please elaborate more
#141 opened by s-github-2 - 0
Brackets in run.sh
#139 opened by eduardobb - 0
Only works with cuda the 7b model
#138 opened by eduardobb - 0
airgapped npm issues in ui container
#137 opened by ifelsefi - 0
Infinite loop "No such file run.sh"
#135 opened by HonneMX - 1
Fresh Install - API Never Starts
#134 opened by f2pc - 3
Running does not work on MacOS with homebrew conda
#130 opened by dylan-sh - 17
- 2
Too heavy for pi 4B
#123 opened by jli113 - 2
Docker compose yields `http: invalid host header`
#127 opened by pabsan-0 - 1
Import documents
#125 opened by zMIMI99 - 0
[Question] Is it possible to add long term memory
#126 opened by zMIMI99 - 1
- 0
Error at win11+wsl2: gguf_init_from_file: invalid magic number 67676a74; error loading model
#119 opened by hwigithub - 5
Unable to run code-34b
#109 opened by coderj001 - 1
Error when running 7B model on WSL2 & Win11
#117 opened by TimyIsCool - 0
/v1/chat/completions max_token should accept null
#113 opened by Ale4224 - 1
docker containers exit codes 0 and 139
#111 opened by avishayil - 0
Unable to build Docker due to network timeout
#112 opened by wessemat - 1
Trap invalid opcode
#110 opened by Kekec852 - 2
Port 3000 taken
#103 opened by mberman84 - 3
Question about hardware requirements
#102 opened by cdmoss - 1
- 4
./run.sh not working.
#106 opened by dingwalnitin - 0
Performance Tweaking - Docker & WSL2
#107 opened by arch1v1st - 2
Only parts of model use GPU acceleration
#105 opened by JamesDConley