|
|
8717526358
|
chore(deps): update ghcr.io/mostlygeek/llama-swap docker tag to v198-vulkan-b8445
|
2026-03-20 22:31:36 +00:00 |
|
|
|
51bc53dbbc
|
chore(deps): update helm release immich to v1.1.2
|
2026-03-20 00:00:50 +00:00 |
|
|
|
ce0b13ebb3
|
change kv cache quant to q8_0
|
2026-03-20 00:57:39 +01:00 |
|
|
|
73d6d1f15a
|
chore(deps): update ghcr.io/mostlygeek/llama-swap docker tag to v198-vulkan-b8400
|
2026-03-19 00:00:34 +00:00 |
|
|
|
8d994e7aa1
|
chore(deps): update ghcr.io/mostlygeek/llama-swap docker tag to v198-vulkan-b8390
|
2026-03-18 00:00:28 +00:00 |
|
|
|
5b551c6c6e
|
switch pullPolicy to Always on crawl4ai-proxy
|
2026-03-17 01:47:29 +01:00 |
|
|
|
7e7b3e3d71
|
add max ctx on llama.cpp
|
2026-03-17 01:33:35 +01:00 |
|
|
|
9f315b38e3
|
use modded crawl4ai proxy image
|
2026-03-17 01:24:09 +01:00 |
|
|
|
82864a4738
|
chore(deps): update ghcr.io/mostlygeek/llama-swap docker tag to v198-vulkan-b8369
|
2026-03-17 00:00:58 +00:00 |
|
|
|
b54c05b956
|
add crawl4ai-proxy for openwebui
|
2026-03-16 20:25:30 +01:00 |
|
|
|
afdada25a0
|
add crawl4ai deployment
|
2026-03-16 19:42:01 +01:00 |
|
|
|
79315d32db
|
add GLM-4.7-Flash model
|
2026-03-16 18:19:28 +01:00 |
|
|
|
a2a5cd72a9
|
configure open webui to use sso from authentik
|
2026-03-16 17:30:16 +01:00 |
|
|
|
c2706a8af2
|
Merge pull request 'chore(deps): update renovate/renovate docker tag to v43.76.1' (#157) from renovate/renovate-renovate-43.x into fresh-start
Reviewed-on: #157
|
2026-03-15 17:40:55 +00:00 |
|
|
|
466932347a
|
chore(deps): update renovate/renovate docker tag to v43.76.1
|
2026-03-15 17:40:29 +00:00 |
|
|
|
afbcea4e82
|
chore(deps): update ghcr.io/mostlygeek/llama-swap docker tag to v198-vulkan-b8352
|
2026-03-15 17:40:26 +00:00 |
|
|
|
20ad26ed31
|
Merge pull request 'chore(deps): update alpine docker tag to v3.23' (#158) from renovate/alpine-3.x into fresh-start
Reviewed-on: #158
|
2026-03-15 17:38:29 +00:00 |
|
|
|
4b4cec10be
|
chore(deps): update ghcr.io/mostlygeek/llama-swap docker tag to v198
|
2026-03-15 00:00:34 +00:00 |
|
|
|
7d90001f18
|
chore(deps): update alpine docker tag to v3.23
|
2026-03-15 00:00:30 +00:00 |
|
|
|
829a5a3fd8
|
add authentik deployment
|
2026-03-14 20:08:48 +01:00 |
|
|
|
cf28dcb5eb
|
add missing allowed renovate command
|
2026-03-14 19:58:35 +01:00 |
|
|
|
d39846422b
|
change gitea port to 80 as workaround of runner bug
|
2026-03-14 15:51:40 +01:00 |
|
|
|
bc4f378df3
|
increase proxy body size on gitea ingress
|
2026-03-14 03:40:17 +01:00 |
|
|
|
db91415017
|
add missing permission to get namespaces to garm
|
2026-03-14 03:04:02 +01:00 |
|
|
|
c5ef5e2273
|
update garm to main branch
|
2026-03-14 02:42:23 +01:00 |
|
|
|
c55c37f0ac
|
add ingress for garm
|
2026-03-14 01:40:11 +01:00 |
|
|
|
168f480c75
|
add gitea actions runner manager
|
2026-03-13 22:37:21 +01:00 |
|
|
|
c056d86da2
|
Add nginx ingress annotation to increase proxy body size limit
|
2026-03-13 04:00:10 +01:00 |
|
|
|
162f5529e2
|
chore(deps): update renovate/renovate docker tag to v43.64.6
|
2026-03-13 04:00:10 +01:00 |
|
|
|
2d295d24e0
|
add 27b q3 variant of qwen3.5
|
2026-03-13 04:00:10 +01:00 |
|
|
|
e8efa9ddc1
|
lower kv cache quant to q4_0 and increase ctx to 64k
|
2026-03-13 04:00:10 +01:00 |
|
|
|
c88dd2899a
|
remove ttl of all models in llama-swap
|
2026-03-13 04:00:10 +01:00 |
|
|
|
8d280bc9dc
|
chore(deps): update renovate/renovate docker tag to v43.60.6
|
2026-03-13 04:00:10 +01:00 |
|
|
|
f219abb74f
|
chore(deps): update ghcr.io/mostlygeek/llama-swap docker tag to v197-vulkan-b8248
|
2026-03-13 04:00:10 +01:00 |
|
|
|
0130991c74
|
refactor: add move llama-swap package config to renovate.json
|
2026-03-13 04:00:10 +01:00 |
|
|
|
966d2c50c0
|
update renovate comment for llama-swap image tag management
|
2026-03-13 04:00:10 +01:00 |
|
|
|
fb4fcc7c12
|
Update renovate/renovate Docker tag to v43.60.4
|
2026-03-13 04:00:10 +01:00 |
|
|
|
af737ab82b
|
Update caddy Docker tag to v2.11.2
|
2026-03-13 04:00:10 +01:00 |
|
|
|
6dc09ec242
|
Update Helm release open-webui to v12.10.0
|
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 |
|
