This website requires JavaScript.
c87893ba6f
Merge pull request #10 from feat/request-priority
main
steve
2026-08-08 01:23:14 +00:00
0358fe321e
internal/router: priority queues so batch jobs yield to interactive requests
feat/request-priority
steve and Claude Opus 5
2026-08-07 02:12:08 -04:00
2f0bb2556e
ci: push immutable sha- and moving main-cuda- tags alongside the version label
steve and Claude Fable 5
2026-07-12 11:25:51 -04:00
fdd89d6580
Merge pull request 'feat(ui): Video playground tab + video capability plumbing' (#2 ) from feat/video-ui into main
steve
2026-07-12 14:56:35 +00:00
1934efb0b5
feat(ui): Video playground tab + video capability plumbing
steve and Claude Fable 5
2026-07-12 10:53:23 -04:00
b83edeb9ef
ci: rebuild fork image on main source pushes, not just build-definition edits
steve and Claude Fable 5
2026-07-12 10:24:00 -04:00
7886758053
Merge pull request 'feat(server): dispatch /v1/videos/sync by model' (#1 ) from feat/video-routes into main
steve
2026-07-12 14:13:05 +00:00
d297852b9e
fix: scope video dispatch to /v1/videos/sync + capture mask
steve and Claude Fable 5
2026-07-12 09:53:33 -04:00
cecb89880e
feat(server): dispatch /v1/videos and /v1/videos/sync by model
steve and Claude Fable 5
2026-07-12 09:25:55 -04:00
0292c90ca1
ci: copy ui-svelte/.npmrc before npm ci in fork-cuda build
steve and Claude Opus 4.8
2026-06-28 12:56:21 -04:00
617c7dc6b9
ci: add Gitea workflow to build fork CUDA image
steve and Claude Opus 4.8
2026-06-28 12:48:48 -04:00
542b79dacf
internal/router/scheduler: add serial scheduler, default on this fork
steve and Claude Opus 4.8
2026-06-28 12:17:32 -04:00
d567fa78cb
npm audit fix
claude/ui-svelte-shading-migration-w30ta6
Benson Wong
2026-06-28 04:38:45 +00:00
187f1ae27a
ui: fix logs tab height and column toggle dropdown
Benson Wong
2026-06-28 04:36:56 +00:00
0ae56b1eb9
ui: convert chat settings panel to a dialog
Benson Wong
2026-06-28 04:22:01 +00:00
e46cbeb2bf
ui: refocus message input after chat generation completes
Benson Wong
2026-06-28 04:16:23 +00:00
a0578f0007
ui: reorganize sidebar and add Settings page
Benson Wong
2026-06-28 03:53:14 +00:00
d207a059a4
ui: enable pagination on Activity page and fix table reactivity
Benson Wong
2026-06-28 03:43:55 +00:00
040ee1e284
ui: convert ActivityTable to shadcn-svelte data-table
Benson Wong
2026-06-28 03:26:24 +00:00
82cad1b84e
ui: add ModelsDash route, clickable sidebar headings, and dialog tweaks
Benson Wong
2026-06-28 03:04:04 +00:00
55c3678906
ui: extract shared ActivityTable and split ModelDetail into components
Benson Wong
2026-06-28 02:27:05 +00:00
8b5a62d92a
ui-svelte: big convert to shadcn components
Benson Wong
2026-06-28 01:53:19 +00:00
d1e4c8ee77
ui tweaks
Benson Wong
2026-06-28 01:21:40 +00:00
11f8afead8
ui: add collapsible Models section to sidebar
Benson Wong
2026-06-27 23:54:18 +00:00
749819ef47
ui: consolidate playground nav into sidebar
Benson Wong
2026-06-27 16:46:10 +00:00
0ab9e74333
ui: finish shadcn migration and remove legacy shim
Claude
2026-06-27 12:10:56 +00:00
b20be6dcd1
ui: convert Image, Speech, Audio interfaces to shadcn buttons
Claude
2026-06-27 12:05:19 +00:00
fc24722258
ui: migrate Rerank and normalize remaining views to shadcn tokens
Claude
2026-06-27 12:01:19 +00:00
2b087dffb1
ui: migrate ChatMessage to shadcn tokens
Claude
2026-06-27 11:58:24 +00:00
746c083a87
ui: migrate chat playground and stats to shadcn
Claude
2026-06-27 11:56:31 +00:00
8dd91e99e8
ui: migrate Activity, Logs views to shadcn
Claude
2026-06-27 11:52:11 +00:00
136dcdc25f
ui: migrate Models panel and Playground to shadcn
Claude
2026-06-27 11:49:16 +00:00
767b8015fa
ui: replace top navbar with shadcn sidebar layout
Claude
2026-06-27 11:46:30 +00:00
f0144a2361
ui: add shadcn-svelte foundation and theming
Claude
2026-06-27 11:42:43 +00:00
0a25b3bd31
AGENTS.md: small tweaks
Benson Wong
2026-06-25 20:31:48 -07:00
32bc781326
internal/config,watcher: add -config-dir (#873 )
v230
Benson Wong
2026-06-24 20:48:51 -07:00
316ad63f76
config,server: add upstream.ignorePaths (#869 )
v229
Benson Wong
2026-06-21 13:49:53 -07:00
e37077a963
feat: hide performance menu item if disabled (#832 )
g2mt
2026-06-21 13:38:29 -07:00
eff9b60434
server: capture failed (non-200) LLM requests (#862 )
Benson Wong
2026-06-20 11:50:35 -07:00
9bcddad91b
internal/server,ui: add new Acitivty page column - Drafted (#859 )
Wojciech
2026-06-19 05:55:02 +02:00
a15e47922c
proxy: meter /upstream requests via metrics middleware (#858 )
v228
Benson Wong
2026-06-17 17:38:52 -07:00
0ab214d1c8
perf: add vendor-agnostic GPU monitoring for Windows (experimental) (#779 )
v227
George
2026-06-17 04:49:09 +00:00
d07b063ab6
internal/server,shared: support request metadata (#850 )
Benson Wong
2026-06-16 21:44:55 -07:00
826210dac9
.coderabbit.yaml: disable unit_tests
Benson Wong
2026-06-16 10:10:17 -07:00
090bb4623c
CodeRabbit Generated Unit Tests: Generate unit tests for PR changes
coderabbitai/utg/6cf1317
coderabbitai[bot]
2026-06-16 12:47:43 +00:00
6cf1317341
schedule,shared: move concurrency 429 limits into scheduler code (#849 )
Benson Wong
2026-06-15 22:35:12 -07:00
8e84b2ec4f
README.md: add macports install option to README (#848 )
Wojciech
2026-06-16 00:58:24 +02:00
ed77385d08
ui: improve manual model load and cancel (#847 )
v226
Benson Wong
2026-06-14 13:38:10 -07:00
92b90447e8
Model capabilities 734 (#842 )
v225
Benson Wong
2026-06-13 23:23:19 -07:00
62aea0e83d
internal/router,server,shared: refactor auth, libs (#839 )
Benson Wong
2026-06-13 10:19:04 -07:00
8c660dcb90
main: gofmt
Benson Wong
2026-06-11 22:16:39 -07:00
f6877b8175
main: show message when listening on network (#836 )
Benson Wong
2026-06-11 22:15:14 -07:00
9b3a33d7b9
Implement new scheduler (#823 )
Benson Wong
2026-06-10 20:34:25 -07:00
0cfe5a6639
Makefile,internal: fix websocket regression and other small things (#830 )
v224
Benson Wong
2026-06-09 21:37:53 -07:00
44e1501e81
internal/process,server: fix unload regression (#828 )
Benson Wong
2026-06-09 20:49:58 -07:00
46cea36bc2
proxy: remove legacy code. Thanks champ 🫡 (#822 )
Benson Wong
2026-06-06 21:00:30 -07:00
ccfba0df28
docker: fix arm64 cpu image downloading amd64 llama-swap binary (#819 )
Benson Wong and Claude
2026-06-04 14:26:21 -07:00
ddfae90b19
Change cron schedule for container builds
Benson Wong
2026-06-04 11:00:43 -07:00
29d3d9ba20
perf: add macOS GPU monitoring via mactop and ioreg (#816 )
v223
Benson Wong
2026-06-03 21:51:03 -07:00
9be9a87fa0
internal/process: improve windows shutdown behaviour (#808 )
v222
Benson Wong
2026-06-01 00:45:30 -07:00
6ea551362e
process,router: make model shutdown and load-streaming robust
v221
Benson Wong
2026-05-31 10:11:12 -07:00
03d58e53fa
Add load testing tool to the UI (#805 )
v220
Benson Wong
2026-05-30 17:04:30 -07:00
c790d0ee03
fix: update the concurrency middleware to respond with a JSON payload (#798 )
Luiszzzor and Ludwik
2026-05-30 08:59:32 +02:00
4ca9c478a2
Makefile,internal/server: various release tweaks
v219
Benson Wong
2026-05-29 15:27:08 -07:00
146a9eab24
ui-svelte: update build directory (#801 )
Benson Wong
2026-05-29 14:45:05 -07:00
02e015fa49
Introduce new routing backend (#790 )
v218
Benson Wong
2026-05-28 21:47:01 -07:00
63bc266395
Add new power draw column header for rocm-smi monitoring (#788 )
Cr4xy
2026-05-25 20:36:16 +02:00
636b53e70f
Improve rocm-smi performance monitoring (#775 )
v217
Cr4xy
2026-05-21 02:59:49 +02:00
59cd3b690d
Added Windows performance monitoring using nvidia-smi (#773 )
gatkisson
2026-05-18 21:02:03 +03:00
5d1e62d224
Disable auto review feature in coderabbit config
Benson Wong
2026-05-18 10:40:21 -07:00
dbb869d019
Increase inactivity thresholds for stale issues
Benson Wong
2026-05-17 22:52:58 -07:00
26bb17e57e
config.example.yaml: Improve matrix vs groups info
Benson Wong
2026-05-17 15:59:25 -07:00
2982dd3d40
ui-svelte: update link to performance discussion thread
v216
Benson Wong
2026-05-17 11:45:56 -07:00
79dc87f881
Add ROCm stats via rocm-smi (#767 )
v215
knguyen298
2026-05-17 09:58:26 -05:00
b2fcc2daa1
ui-svelte: fix cached tokens total counting -1 sentinel (#760 )
v214
krzychdre
2026-05-15 23:42:44 +02:00
6a9c4efc8f
fix: use --loop instead of -loop for nvidia-smi (driver 540+ compat) (#759 )
cdwaage
2026-05-15 13:20:29 -07:00
0c813e44d1
ui-svelte: package updates
v213
Benson Wong
2026-05-14 21:56:04 -07:00
fe71e8a6ea
proxy,ui-svelte: improve support for v1/messages and v1/responses (#758 )
Benson Wong
2026-05-14 21:53:57 -07:00
aac7b8745a
ci: set go-version-file in release workflow
v212
Benson Wong
2026-05-13 22:12:02 -07:00
4e606feff0
ci: fix workflow bugs in release and go-ci
Benson Wong
2026-05-13 21:48:27 -07:00
a4b91e08cf
Changes and fixes before the release (docs/small tweaks) (#750 )
Benson Wong
2026-05-13 21:18:19 -07:00
3e3646f9f9
perf: ignore LACT devices reporting zero VRAM (#753 )
David Soušek and David Soušek
2026-05-13 19:03:54 +02:00
a01afe261b
ci: use manifest-aware cleanup action for multi-arch :cpu (#751 )
rhtenhove
2026-05-13 03:04:46 +02:00
174e8562aa
Multi arch cpu (#746 )
rhtenhove
2026-05-12 06:03:48 +02:00
085b54bc88
proxy: fix data race in /running endpoint and typo in error message (#748 )
Abdulazez A.
2026-05-11 22:49:18 +03:00
2be3416baa
ui: add auto theme switch mode based on system theme (#741 )
bankjaneo
2026-05-10 10:22:18 +07:00
7e3e94a08a
proxy,ui: add performance monitoring with Prometheus metrics (#743 )
Benson Wong
2026-05-09 13:29:22 -07:00
e261745c66
proxy: add versionless API endpoint (#733 )
Wim Vander Schelden
2026-05-03 22:47:38 +02:00
11b7913287
llama-swap.go: remove debounce, replace fmt.Printlns (#731 )
Benson Wong
2026-05-02 16:28:53 -07:00
c79114d40a
proxy: fix logger not checking matrix for processes
v211
Marcus
2026-05-01 16:43:20 -07:00
430166d5eb
proxy: fix zero duration for non streaming responses (#723 )
v210
Benson Wong
2026-04-30 19:51:28 -07:00
5b4beaceef
fix: ?no-history flag and improve /logs monitoring docs (#721 )
Marcus
2026-04-30 00:50:36 -07:00
fd3c28ffc5
Refactor Activity Page (#710 )
v209
Benson Wong
2026-04-28 20:33:03 -07:00
a846c4f18c
config: remove hard cap on macro length (#718 )
Quentin Machu
2026-04-28 16:32:54 -04:00
5bae33a769
ui-svelte: default theme to user preferred color scheme (#712 )
Marcus
2026-04-27 06:44:22 -07:00
8f4ff01f93
ui-svelte: make it easier to toggle panels in logs view
Benson Wong
2026-04-26 22:12:43 -07:00
e8d4384cd2
ui-svelte: support reasoning and reasoning_content (#708 )
v208
Benson Wong
2026-04-26 13:11:48 -07:00
ce28485be2
ui-svelte: add prompt processing histogram (#705 )
Benson Wong
2026-04-25 16:13:07 -07:00
3cd7837b1f
fix: support architecture-specific download URLs in install script (#698 )
Damir
2026-04-24 03:05:33 +02:00
0b31ccacc1
ui-svelte: fix histogram calculation (#695 )
v207
v206
Benson Wong
2026-04-22 23:42:39 -07:00