|
|
0c619a4005
|
chore(deps): update renovate/renovate docker tag to v43.64.6
|
2026-03-12 16:47:00 +00:00 |
|
|
|
9cfb599c7d
|
add 27b q3 variant of qwen3.5
|
2026-03-11 02:15:24 +01:00 |
|
|
|
311f0362a8
|
lower kv cache quant to q4_0 and increase ctx to 64k
|
2026-03-10 14:02:17 +01:00 |
|
|
|
46c752773f
|
remove ttl of all models in llama-swap
|
2026-03-10 13:48:10 +01:00 |
|
|
|
c1b1fb7315
|
Merge pull request 'chore(deps): update renovate/renovate docker tag to v43.60.6' (#150) from renovate/renovate-renovate-43.x into fresh-start
Reviewed-on: #150
|
2026-03-10 12:16:28 +00:00 |
|
|
|
95012b1fc1
|
chore(deps): update renovate/renovate docker tag to v43.60.6
|
2026-03-10 12:14:14 +00:00 |
|
|
|
77d1a4bb34
|
chore(deps): update ghcr.io/mostlygeek/llama-swap docker tag to v197-vulkan-b8248
|
2026-03-10 12:14:09 +00:00 |
|
|
|
eb33cad5c6
|
refactor: add move llama-swap package config to renovate.json
|
2026-03-10 13:13:38 +01:00 |
|
|
|
6b012e01a8
|
update renovate comment for llama-swap image tag management
|
2026-03-10 12:55:03 +01:00 |
|
|
|
77097bf81d
|
Merge pull request 'Update renovate/renovate Docker tag to v43.60.4' (#145) from renovate/renovate-renovate-43.x into fresh-start
Reviewed-on: #145
|
2026-03-10 11:54:05 +00:00 |
|
|
|
82029fa745
|
Merge pull request 'Update caddy Docker tag to v2.11.2' (#147) from renovate/caddy-2.x into fresh-start
Reviewed-on: #147
|
2026-03-10 11:53:51 +00:00 |
|
|
|
f394b06006
|
Update renovate/renovate Docker tag to v43.60.4
|
2026-03-10 00:00:44 +00:00 |
|
|
|
be8e6d8990
|
Update Helm release open-webui to v12.10.0
|
2026-03-10 00:00:42 +00:00 |
|
|
|
2df8303905
|
add qwen3.5 4b heretic
|
2026-03-08 21:39:53 +01:00 |
|
|
|
65c11ab4ca
|
add glm-5 from openrouter to llama-swap
|
2026-03-08 17:58:01 +01:00 |
|
|
|
55da75f06e
|
clean up llama-swap config
|
2026-03-08 17:25:44 +01:00 |
|
|
|
ac0165cf01
|
adjust parameters of qwen3-coder-next
|
2026-03-07 22:52:49 +01:00 |
|
|
|
15989f4891
|
automatically fit context on qwen3.5 2b and 4b
|
2026-03-07 21:01:32 +01:00 |
|
|
|
1b11201ad0
|
Update caddy Docker tag to v2.11.2
|
2026-03-07 00:00:27 +00:00 |
|
|
|
a3ebc531fe
|
Add Q3_K_M variand of Qwen3.5-9B
|
2026-03-06 23:21:58 +01:00 |
|
|
|
63f154293d
|
fiix thinking versions of Qwen3.5 small
|
2026-03-06 23:17:48 +01:00 |
|
|
|
42aa0a7263
|
set strategy to recreate on llama-swap deployment
|
2026-03-06 23:08:03 +01:00 |
|
|
|
a9b8b45328
|
add 2B, 4B, 9B versions of Qwen3.5 in thinking + nonthinking variants
|
2026-03-06 23:07:02 +01:00 |
|
|
|
3dc481bc8b
|
increase target margin of 2048MB of VRAM
|
2026-03-06 02:41:34 +01:00 |
|
|
|
711c437c0a
|
add Qwen3.5 Small 0.8B model and replace Qwen3-VL-2B as task model
|
2026-03-05 23:17:30 +01:00 |
|
|
|
975f1db8f5
|
shorten context for qwen3-vl-2b and lower kv cache quant
|
2026-03-05 22:42:54 +01:00 |
|
|
|
ab9ddd0f3b
|
add path to mmproj in qwen3.5 heretic
|
2026-03-05 19:31:03 +01:00 |
|
|
|
3e59786c83
|
manually update llama-swap image tag
|
2026-03-05 19:27:45 +01:00 |
|
|
|
2d743e0de0
|
Merge pull request 'Update Helm release immich to v1.1.1' (#139) from renovate/immich-1.x into fresh-start
Reviewed-on: #139
|
2026-03-02 17:26:36 +00:00 |
|
|
|
0a1c0a65e1
|
Merge pull request 'Update renovate/renovate Docker tag to v43.46.6' (#140) from renovate/renovate-renovate-43.x into fresh-start
Reviewed-on: #140
|
2026-03-02 17:26:29 +00:00 |
|
|
|
96a09ae6f9
|
Merge pull request 'Update caddy Docker tag to v2.11.1' (#141) from renovate/caddy-2.x into fresh-start
Reviewed-on: #141
|
2026-03-02 17:26:21 +00:00 |
|
|
|
5c4535beb6
|
Add mmproj-url for Qwen3.5-35B-A3B-heretic model
|
2026-03-02 03:19:16 +01:00 |
|
|
|
cd513489a2
|
Update renovate/renovate Docker tag to v43.46.6
|
2026-03-02 00:00:28 +00:00 |
|
|
|
44aa0c8136
|
add gemma-3-270m-it-qat model
|
2026-02-28 23:20:13 +01:00 |
|
|
|
902004f2e7
|
Add Qwen3.5-35B-A3B-heretic models
|
2026-02-28 18:33:42 +01:00 |
|
|
|
bf1f1c0b41
|
Add always loaded Qwen3-VL-2B-Instruct
|
2026-02-28 17:48:20 +01:00 |
|
|
|
5915b8dd30
|
Add Qwen3.5-35-A3B model
|
2026-02-28 15:49:59 +01:00 |
|
|
|
c14257842a
|
automatically fit models by llama.cpp
|
2026-02-26 01:38:39 +01:00 |
|
|
|
d053342234
|
fix models mount
|
2026-02-26 01:25:21 +01:00 |
|
|
|
2dbd964c28
|
add schema reference to config.yaml
|
2026-02-26 00:43:16 +01:00 |
|
|
|
7712aac0f5
|
configure llama-swap to log llama.cpp output
|
2026-02-26 00:39:58 +01:00 |
|
|
|
c7bc79f574
|
add Qwen3-Coder-Next model
|
2026-02-26 00:10:53 +01:00 |
|
|
|
6cba277b9d
|
update llama-swap image
|
2026-02-25 19:07:10 +01:00 |
|
|
|
1ca79d5262
|
disable built in open-webui ingress
|
2026-02-25 18:20:27 +01:00 |
|
|
|
95ca2aa54f
|
increase openwebui storage to 10Gi
|
2026-02-25 17:41:23 +01:00 |
|
|
|
bfb089aeff
|
migrate llama models to ssd
|
2026-02-25 16:03:12 +01:00 |
|
|
|
ed83a66a83
|
add ssd volume for llama models
|
2026-02-25 15:43:42 +01:00 |
|
|
|
fa7b35326c
|
add openwebui
|
2026-02-25 15:21:04 +01:00 |
|
|
|
b4ba66dc18
|
Update caddy Docker tag to v2.11.1
|
2026-02-24 00:00:41 +00:00 |
|
|
|
74b2436694
|
Update Helm release immich to v1.1.1
|
2026-02-23 00:05:23 +00:00 |
|
