Auto updated submodule references

2026-02-08 05:31:37 +00:00 · 2026-01-26 12:23:15 -05:00 · 2026-02-08 05:31:37 +00:00 · 2026-02-08 05:31:37 +00:00 · 2026-01-26 12:19:23 -05:00 · 2026-01-20 10:44:05 -05:00
diff --git a/.forgejo/workflows b/.forgejo/workflows
Git bot 4d4c33d21e All checks were successful / build-swap (push) Successful in 43s Details / build-comfyui (push) Successful in 28m12s Details / build-llama-server (push) Successful in 1h32m45s Details / build-vllm (push) Successful in 45s Details / build-ik-llama-server (push) Successful in 2h6m29s Details / build-combined (push) Successful in 44m12s Details Auto updated submodule references		2026-02-08 05:31:37 +00:00
.forgejo/workflows	Update run script to direcly use uvcorn to try to make unloading more reliable also pick up script changes in container rebuilds	2026-01-26 12:23:15 -05:00
ComfyUI@f350a84261	Auto updated submodule references	2026-02-08 05:31:37 +00:00
config-gen
ik_llama.cpp@e22b2d1246	Auto updated submodule references	2026-02-08 05:31:37 +00:00
litellm-llama-swap-terraform@462f36a674	Bring in new tf code	2026-01-26 12:19:23 -05:00
llama-swap@58cb7bc820	Readded llama-swap from github branch	2026-01-20 10:44:05 -05:00
llama.cpp@9a5f57795c	Auto updated submodule references	2026-02-08 05:31:37 +00:00
prompt-templates	Attempt at this with chatml template bits	2026-02-04 15:35:40 -05:00
swap-configs	Add Q6 and 256k model	2026-02-05 08:55:55 -05:00
vllm-mirror@b5f8c3092d	Bring in updates, vllm broke for some reason around anthropic calls	2026-02-01 08:20:10 -05:00
.gitmodules	Add a build for ik-llama-server, doesnt use it yet need to examine still	2026-01-24 06:42:22 -05:00
AGENTS.md
base-image.Containerfile	remove the temporary hack to rbeuild the base earlier than planned	2026-01-26 14:36:26 -05:00
combined.Containerfile	go ahead and remove vllm-omni, not using it and annoying	2026-02-01 18:39:05 -05:00
comfyui-image.Containerfile	Temporary notes and changes for qwen3tts comfy	2026-01-26 19:26:52 -05:00
compose-base.yml	Upgrade again, maybe have working Q3CN but not likely	2026-02-04 19:39:06 -05:00
compose-brainiac.yml	refactor compose file to try to make it DRY	2026-01-27 13:04:06 -05:00
compose-manchester.yml	Refactor the layout to enable better reload support	2026-01-18 07:27:49 -05:00
data.json
ik-llama-server.Containerfile	Add a build for ik-llama-server, doesnt use it yet need to examine still	2026-01-24 06:42:22 -05:00
llama-server.Containerfile	Also do all the others, lets debug	2026-01-21 12:55:58 -05:00
llama-swap.Containerfile
notes_for_comfyui-qwen3-tts.txt	Temporary notes and changes for qwen3tts comfy	2026-01-26 19:26:52 -05:00
qwen3-tts-server.sh	Doh! use exec to make unloading work more reliably!	2026-01-26 12:45:42 -05:00
README.md
run-comfy.sh	Doh! use exec to make unloading work more reliably!	2026-01-26 12:45:42 -05:00
send_komodo_webhook.sh
vllm-image.Containerfile	Fix version in vllm build	2026-02-01 18:38:09 -05:00