Wolfram Ravenwolf

### Describe the bug With [Change GPTQ triton default settings · 7438f4f](https://github.com/oobabooga/text-generation-webui/commit/7438f4f6ba28f36d59da5132a5bcf5edb10742d4) did you invert the GPTQ triton flags and they should now be off by default. However, when using...

Fixed, improved, and unified Docker environment

2

## Checklist: - [x] I have read the [Contributing guidelines](https://github.com/oobabooga/text-generation-webui/wiki/Contributing-guidelines). ## Fixed and improved Docker environment - Unified Dockerfile: - Moved GPU_CHOICE from RUN to ARG instruction so all the...

How to make a PR to fix a modelfile?

2

Couldn't find the modelfiles in this repo, but would like to fix and make a PR for the Mixtral modelfile. Its prompt format is wrong, fixed it locally, but how...

[BUG] Harvester management VIP address not working after rebooting nodes

3

**Describe the bug** After setting up a multi-node Harvester cluster, I rebooted the nodes. The management VIP address does not come up unless I start the node that held the...

Fix: Disable proxy_buffering

2

### TL;DR: This PR disables proxy_buffering in Nextcloud's example Docker setups to fix large file (>1GB) download failures over slower network connections, reverting a recent breaking change within nginx-proxy. ####...

text-generation-webui API chat completion broken (selects ooba assistant, ignored sysprompt and template)

2

**Describe the bug** text-generation-webui API chat completion broke completely after I tried using a "Generation Preset/Character Name" of my own. Even after removing it, it's not working anymore, even after...