Commit Graph

54 Commits

Author SHA1 Message Date
af737ab82b Update caddy Docker tag to v2.11.2 2026-03-13 04:00:10 +01:00
39fc38d62b add qwen3.5 4b heretic 2026-03-13 04:00:10 +01:00
e72a79be8f add glm-5 from openrouter to llama-swap 2026-03-13 04:00:10 +01:00
4fda343b01 clean up llama-swap config 2026-03-13 04:00:10 +01:00
266ced7362 adjust parameters of qwen3-coder-next 2026-03-13 04:00:10 +01:00
8a074839b1 automatically fit context on qwen3.5 2b and 4b 2026-03-13 04:00:10 +01:00
42038207fc Add Q3_K_M variand of Qwen3.5-9B 2026-03-13 04:00:10 +01:00
28cb53c031 fiix thinking versions of Qwen3.5 small 2026-03-13 04:00:10 +01:00
88a73cbb41 set strategy to recreate on llama-swap deployment 2026-03-13 04:00:10 +01:00
46a7e24932 add 2B, 4B, 9B versions of Qwen3.5 in thinking + nonthinking variants 2026-03-13 04:00:10 +01:00
cd7ebac6b9 increase target margin of 2048MB of VRAM 2026-03-13 04:00:10 +01:00
ba9db6ce41 add Qwen3.5 Small 0.8B model and replace Qwen3-VL-2B as task model 2026-03-13 04:00:10 +01:00
6dd9a717e2 shorten context for qwen3-vl-2b and lower kv cache quant 2026-03-13 04:00:10 +01:00
c67b6f7ebe add path to mmproj in qwen3.5 heretic 2026-03-13 04:00:10 +01:00
8d7cf402fd manually update llama-swap image tag 2026-03-13 04:00:10 +01:00
b22498c60f Update caddy Docker tag to v2.11.1 2026-03-13 04:00:10 +01:00
78a81c5b72 Add mmproj-url for Qwen3.5-35B-A3B-heretic model 2026-03-13 04:00:10 +01:00
2bb23c4ed0 add gemma-3-270m-it-qat model 2026-03-13 04:00:10 +01:00
8c29fc8018 Add Qwen3.5-35B-A3B-heretic models 2026-03-13 04:00:10 +01:00
2836542569 Add always loaded Qwen3-VL-2B-Instruct 2026-03-13 04:00:10 +01:00
1e68450d8a Add Qwen3.5-35-A3B model 2026-03-13 04:00:10 +01:00
2c83eb26b3 automatically fit models by llama.cpp 2026-03-13 04:00:10 +01:00
ec038d7154 fix models mount 2026-03-13 04:00:10 +01:00
b61e3b5c08 add schema reference to config.yaml 2026-03-13 04:00:10 +01:00
59bf4a1aa6 configure llama-swap to log llama.cpp output 2026-03-13 04:00:10 +01:00
63a8e2f7ac add Qwen3-Coder-Next model 2026-03-13 04:00:10 +01:00
1ddef7951a update llama-swap image 2026-03-13 04:00:10 +01:00
9f55d67ffa migrate llama models to ssd 2026-03-13 04:00:10 +01:00
3ffadc8628 add ssd volume for llama models 2026-03-13 04:00:10 +01:00
a3f30873f9 switch llama models dir to lvm hdd 2026-03-13 04:00:09 +01:00
96e5202e6d add lvm hdd llama models pvc 2026-03-13 04:00:09 +01:00
9032060930 add abliterated versions of qwen3-vl 2026-03-13 04:00:08 +01:00
f13c3ae3e7 Add 8B and 2B variants of qwen3-vl 2026-03-13 04:00:08 +01:00
669beccc35 fix Qwen3-VL-4B-Instruct-GGUF models looping issue 2026-03-13 04:00:08 +01:00
5eb7b7bb0c add qwen3-vl thinking variant 2026-03-13 04:00:08 +01:00
0b677d0faf add qwen3-vl, fix librechat taking over settings and clean up llama config 2026-03-13 04:00:08 +01:00
e3325670de fix cache location after llama-swap update 2026-03-13 04:00:08 +01:00
b9200d3a4c update llama-swap 2026-03-13 04:00:08 +01:00
8063cbaf80 update llama-swap docker image 2026-03-13 04:00:08 +01:00
77ebe2cc89 Update caddy Docker tag to v2.10.2 2026-03-13 04:00:08 +01:00
9544f4719f Add Qwen2.5-VL models 2026-03-13 04:00:07 +01:00
eb4ac7acf4 add qwen3-4b-2507 model 2026-03-13 04:00:07 +01:00
60fafe2a91 move all ingresses to new nginx ingress 2026-03-13 04:00:07 +01:00
feaf805208 update llama-swap 2026-03-13 04:00:07 +01:00
93855dc712 llama automatic unloading and longer start timeout 2026-03-13 04:00:07 +01:00
241dce4524 disable warmups 2026-03-13 04:00:07 +01:00
17805e6b31 add gemma3 model 2026-03-13 04:00:07 +01:00
6f3e612dde move llama models to ssd 2026-03-13 04:00:07 +01:00
32eea7c3af add gemma3n 2026-03-13 04:00:07 +01:00
de3ef465f0 add qwen3 no thinking 2026-03-13 04:00:07 +01:00