ssongliu
7120faad76
fix: correct Fail2ban form config reads and updates ( #14477 )
2026-11-19 14:17:09 +08:00
ssongliu
faeb39f5c6
fix(vllm): extend GB10 lifecycle startup timeout ( #14468 )
2026-11-18 15:57:25 +08:00
ssongliu
0380c7c1eb
feat(vm): support data disks and safe snapshot recovery ( #14465 )
2026-11-18 13:45:45 +08:00
ssongliu
148e1981b0
feat(postgresql): add user and database authorization management ( #14460 )
...
* feat(postgresql): add user and database authorization management
* fix(postgresql): reuse existing roles during app recovery
2026-11-18 09:53:22 +08:00
ssongliu
6d8d3b25b1
feat: improve model chat actions and instance alias labels ( #14461 )
2026-11-17 16:15:34 +08:00
ssongliu
d81ac75e0c
feat(vllm): support Qwen3.8 GB10 version and organize translations ( #14458 )
2026-11-17 12:51:23 +08:00
ssongliu
b00478c312
fix(vllm): show stopped status when containers are removed ( #14451 )
2026-11-16 15:33:21 +08:00
ssongliu
bb87e1e816
fix(ai): persist model service verification status ( #14450 )
2026-11-16 14:49:32 +08:00
ssongliu
1de2877d49
fix(vllm): align GB10 images and upgrade version comparison ( #14448 )
2026-11-16 13:39:50 +08:00
ssongliu
5fbec27256
fix(i18n): correct locale formatting errors ( #14445 )
2026-11-16 10:42:10 +08:00
ssongliu
4eec4df043
fix(ai): clarify benchmark tokenizer selection hints ( #14444 )
2026-11-16 10:32:37 +08:00
ssongliu
0b0c8cbc74
feat(vllm): support TileLang GB10 image ( #14443 )
2026-11-15 16:26:04 +08:00
ssongliu
c4ff0603ca
feat: support four-node GB10 vLLM versions and model hints ( #14441 )
2026-11-15 00:41:31 +08:00
ssongliu
6f89c03456
fix: reset pro state when switching to community nodes ( #14430 )
2026-11-13 18:13:54 +08:00
ssongliu
97fafa7a80
feat(vllm): localize image selection and preview labels ( #14428 )
...
* feat(vllm): localize image selection and preview labels
* feat(vllm): localize standard and custom image types
2026-11-13 15:29:07 +08:00
ssongliu
92c3173aec
feat(ai): sync gateway providers and model discovery ( #14426 )
...
* feat(ai): sync gateway providers and model discovery
Add provider account types and protocol-aware model discovery, and replace predefined models with editable model pools.
Align provider icons with AI Gateway, preserve international Coding Plan restrictions, and filter account counts consistently with selectable accounts.
* fix(ai): preserve Ollama base paths during model discovery
* fix(ai): restore custom DashScope image protocol support
2026-11-13 14:04:11 +08:00
ssongliu
a922e5bfae
fix: isolate GPU monitoring failures and scope device warnings ( #14421 )
2026-11-12 23:27:43 +08:00
ssongliu
806de6307b
feat(ai): add streaming model chat drawer ( #14412 )
2026-11-12 15:58:09 +08:00
ssongliu
ad51a8d026
fix: match dual GB10 vLLM version suffix ( #14407 )
2026-11-11 21:46:35 +08:00
ssongliu
5afcedc235
fix(vllm): unify default images and upgrade suffix rules ( #14406 )
2026-11-11 21:19:22 +08:00
ssongliu
7f91e7cb67
fix(gpu): compact group cards and order by topology ( #14404 )
2026-11-11 18:56:19 +08:00
ssongliu
bf4d923135
feat(vllm): support external instances in dashboard monitoring ( #14402 )
2026-11-11 17:59:33 +08:00
ssongliu
3adee94458
feat(vllm): integrate instance monitoring lifecycle and settings ( #14391 )
2026-11-10 20:56:28 +08:00
ssongliu
c3c1612bef
fix(cmd): align simple password validation with frontend ( #14384 )
2026-11-10 17:38:50 +08:00
ssongliu
d0439ea9b2
fix(ai): expose sanitized verification errors and clarify vLLM authentication ( #14388 )
2026-11-10 17:38:34 +08:00
ssongliu
8b712d2c16
fix: reduce terminal revocation logs and skip enterprise update checks ( #14383 )
2026-11-10 16:21:48 +08:00
ssongliu
aec5684184
feat(ai): streamline GPU groups and NUMA configuration ( #14381 )
2026-11-10 15:27:38 +08:00
ssongliu
a4572e0ca4
fix: correct backup account name search ( #14375 )
2026-11-10 10:42:21 +08:00
ssongliu
e65a9d9939
feat(gpu): show shared system memory usage in overview ( #14373 )
2026-11-10 10:17:27 +08:00
ssongliu
dc0c00b04a
feat(ai): unify GPU group layout and clarify single-sample labels ( #14372 )
2026-11-10 10:02:46 +08:00
ssongliu
79f07333b0
feat(ai): clarify vLLM metrics and refine GPU configuration ( #14371 )
2026-11-09 23:53:02 +08:00
ssongliu
528486cabd
fix(ai): unify GPU detection and improve group topology ( #14367 )
2026-11-09 18:20:37 +08:00
ssongliu
d5e3c7a820
fix(auth): restore access after re-enabling security entrance ( #14364 )
2026-11-09 16:39:17 +08:00
ssongliu
c31898e666
fix(ntp): preserve UTC offset when synchronizing system time ( #14363 )
...
Fixes #14265
2026-11-09 16:37:59 +08:00
ssongliu
e960b1340b
fix(ssh): restore automatic terminal key generation ( #14359 )
2026-11-09 16:37:45 +08:00
ssongliu
ed182b5408
feat(ai): add peak analysis ( #14358 )
2026-11-09 14:17:47 +08:00
ssongliu
9a83fa4af2
feat(ai): add GPU groups and NUMA binding ( #14348 )
...
* feat(ai): add GPU groups and NUMA binding
* fix(ai): normalize NVIDIA GPU index aliases before validation
2026-11-09 09:54:02 +08:00
ssongliu
8ed1bf0eda
feat(gpu): show aggregate memory usage in monitor summary ( #14349 )
2026-11-08 22:30:50 +08:00
ssongliu
5c71dcba19
feat(ai): share compose preview helpers and translations ( #14342 )
2026-11-08 17:24:01 +08:00
ssongliu
c5dfcae38b
feat(ai): add model deployment naming help translations ( #14341 )
2026-11-08 15:56:26 +08:00
ssongliu
3c1f2a64b4
fix(ai): simplify GPU status and add benchmark log translations ( #14334 )
2026-11-07 22:58:14 +08:00
ssongliu
94e2ee5403
fix: refine GPU monitor layout and vendor environment checks ( #14333 )
2026-11-07 19:21:35 +08:00
ssongliu
1927e68010
fix: align model deployment config and GPU environment status ( #14332 )
2026-11-07 17:14:21 +08:00
ssongliu
ab506e4a3b
feat(container): add NVIDIA GPU runtime configuration switch ( #14331 )
2026-11-07 15:39:38 +08:00
ssongliu
726fd94e07
fix(dashboard): improve vLLM monitoring display and preserve samples ( #14326 )
2026-11-06 23:44:30 +08:00
ssongliu
ea31289da3
feat(dashboard): add vLLM token throughput monitoring ( #14325 )
2026-11-06 21:47:02 +08:00
ssongliu
d7783e72cb
fix(ai): clarify benchmark image pull and model directory hints ( #14319 )
...
* fix(ai): clarify benchmark image pull and model directory hints
* feat(ai): update model and tokenizer directory guidance
2026-11-06 18:02:26 +08:00
ssongliu
8a68d30dcb
feat(ai): refine model service details and container log streaming ( #14317 )
2026-11-06 16:00:40 +08:00
ssongliu
23a54653f8
fix(ai): persist model verification settings and reset lifecycle status ( #14312 )
...
* fix(ai): persist model verification settings and reset lifecycle status
* fix(ai): reset model verification before upgrade cutover
2026-11-06 00:44:50 +08:00
ssongliu
56ecd56c6d
feat(ai): refine model lists and sync status hints ( #14309 )
2026-11-05 18:29:01 +08:00
ssongliu
024a246a46
refactor(ai): align menu order and simplify model routes ( #14308 )
2026-11-05 17:08:15 +08:00
ssongliu
fe3953963e
refactor(ai): move model preparation to XPack and reorganize model views ( #14306 )
2026-11-05 16:27:06 +08:00
ssongliu
51bae946e1
feat(ai): refine model service terminology and provider setup ( #14305 )
2026-11-05 14:58:17 +08:00
ssongliu
730dbbab5b
fix(vllm): distinguish empty metrics from collection failures ( #14303 )
2026-11-04 20:42:58 +08:00
ssongliu
2e9c1794f2
feat: separate model services into a standalone menu ( #14300 )
2026-11-04 17:23:21 +08:00
ssongliu
d1059c7356
feat(ai): link model downloads to recipe search ( #14298 )
2026-11-04 16:43:29 +08:00
ssongliu
b07afd3785
feat(ai): improve model preparation and download progress refresh ( #14297 )
2026-11-04 16:11:16 +08:00
ssongliu
89787a55ee
feat(ai): refine model deployment UI and support GB10 upgrades ( #14295 )
2026-11-04 12:28:30 +08:00
ssongliu
5b9aaa7d7a
fix(ai): use default buttons for additional model counts ( #14294 )
2026-11-04 10:02:09 +08:00
ssongliu
30381a3c68
feat(ai): streamline deployments and add local model selection ( #14293 )
...
* feat(ai): split model management and add weight provider filters
* feat(ai): streamline deployments and add local model selection
2026-11-03 23:54:22 +08:00
ssongliu
daae8c43f8
refactor: remove Fxplay and TensorRT-LLM support ( #14287 )
2026-11-03 14:38:15 +08:00
ssongliu
133a02741a
feat(vm): promote virtual machines to a top-level menu ( #14286 )
...
Migrate existing VM menus directly to the top level and preload permission-filtered menus on login. Coordinate menu refreshes during node switching and retain only sidebar preferences in persisted state.
2026-11-03 11:41:08 +08:00
ssongliu
fac15e3292
fix(ai): refine model service forms and Ollama drawers ( #14283 )
2026-11-03 00:07:38 +08:00
ssongliu
2401bb16a2
feat(ai): connect local model accounts and add Ollama management page ( #14282 )
...
* feat(ai): connect local model accounts and add Ollama management page
* fix(ai): register Ollama management frontend path
2026-11-02 22:16:43 +08:00
ssongliu
c06c4e338b
feat(vm): enable community virtual machines and migrate xpack data ( #14279 )
...
* feat(vm): enable community virtual machines and migrate xpack data
* fix(vm): stop ISO download polling on failure or cancellation
* fix(vm): respect deleteFile when deleting failed ISO imports
2026-11-02 18:22:58 +08:00
ssongliu
f8c61993c5
feat(ai): open source model marketplace and migrate historical data ( #14277 )
...
* feat(ai): open source model marketplace and migrate historical data
* fix(ai): wait for canceled model downloads before retrying
2026-11-02 17:46:26 +08:00
ssongliu
b31e683f1b
fix: correct local inference engine operation task logs ( #14274 )
2026-11-02 17:27:43 +08:00
ssongliu
51cf40a648
feat(ai): show local inference engine ports ( #14273 )
2026-11-02 11:21:17 +08:00
ssongliu
13362f84a6
fix(ai): synchronize inference engine task states and unify management ( #14269 )
2026-11-01 23:36:15 +08:00
ssongliu
046dc94d05
fix(script): bypass stale resource caches during library sync ( #14268 )
2026-11-01 22:32:58 +08:00
ssongliu
2059119d89
fix(dashboard): restore monitor layout and compact single GPU status ( #14267 )
2026-11-01 22:32:06 +08:00
ssongliu
7f4c503982
fix(ai): improve GPU capability hints and separate engine logs ( #14263 )
2026-11-01 01:06:37 +08:00
ssongliu
93ebc6a8b9
feat(ai): streamline Ollama model pool management ( #14259 )
2026-10-30 23:50:11 +08:00
ssongliu
7156addf79
feat(ai): refine model pools, navigation and GPU deployment configuration ( #14257 )
2026-10-30 23:00:23 +08:00
ssongliu
c6329a62db
feat(dashboard): refine monitoring, quick access and installation messages ( #14256 )
2026-10-30 22:46:20 +08:00
ssongliu
3f594bd7a2
feat: compact dashboard GPU layout for four devices ( #14255 )
2026-10-30 18:10:30 +08:00
ssongliu
02031e4d7c
feat: support GB10 shared memory and refine AI model UI ( #14254 )
2026-10-30 18:09:51 +08:00
ssongliu
2f7bab67b3
feat(ai): add unified GPU configuration and collapsible deployment cards ( #14253 )
2026-10-30 17:03:21 +08:00
ssongliu
2d473042fc
style(login): update enterprise login background ( #14252 )
2026-10-30 16:50:34 +08:00
ssongliu
8885463a75
feat(dashboard): add system and GPU status views ( #14251 )
2026-10-30 15:18:44 +08:00
ssongliu
01feaa6059
fix(ai): allow stopping and deleting restarting model containers ( #14250 )
2026-10-30 12:52:32 +08:00
ssongliu
ecb264f087
fix(ai): clean up local model accounts during uninstall ( #14249 )
...
* fix(ai): clean up local model accounts during uninstall
* refactor(ai): restore best-effort local model account cleanup
2026-10-30 12:10:59 +08:00
ssongliu
87ab399bcc
feat(ai): add download source icons and localize downloads labels ( #14240 )
2026-10-29 11:23:09 +08:00
ssongliu
d7c42e3e8b
fix(ai): unify model deletion prompts and register template route ( #14233 )
2026-10-28 18:20:06 +08:00
ssongliu
8684a26459
feat(ai): refine model navigation and downloader translations ( #14228 )
2026-10-28 12:11:41 +08:00
ssongliu
3a7cd211af
fix: unify database credential validation ( #14216 )
2026-10-27 23:06:13 +08:00
ssongliu
bd0bc0079e
refactor(ai): remove obsolete tokenizer directory patterns ( #14225 )
2026-10-27 23:05:54 +08:00
ssongliu
93ed58d784
fix(terminal): improve dock button border in dark mode ( #14224 )
2026-10-27 17:22:51 +08:00
ssongliu
8d320ef2ca
feat(node): add translations for existing node packages ( #14222 )
2026-10-27 17:12:14 +08:00
ssongliu
b3c1e0df42
refactor(frontend): use DialogPro for task logs ( #14212 )
2026-10-27 14:34:20 +08:00
ssongliu
5346d5f58a
fix(ai): reconcile Ollama models and improve engine management ( #14211 )
2026-10-27 11:06:32 +08:00
ssongliu
7c7fd492c4
feat(ai): support benchmark report routes and parameter translations ( #14210 )
2026-10-26 23:33:17 +08:00
ssongliu
fbf66766c2
fix: align AI menu order and labels ( #14192 )
2026-10-26 14:03:40 +08:00
ssongliu
9481a7535d
fix: align AI menu order and labels ( #14183 )
2026-10-26 11:29:20 +08:00
ssongliu
14be5b7870
feat(ai): translate benchmark comparison metrics ( #14182 )
2026-10-25 14:05:09 +08:00
ssongliu
c4b76a8e89
feat(ai): unify model services and inference engine management ( #14175 )
2026-10-23 18:39:22 +08:00
ssongliu
a393224729
feat(ai): support benchmark node options and report integration ( #14145 )
2026-10-21 18:07:39 +08:00
ssongliu
175fbaf3f2
fix: correct terminal node routing for containers ( #14142 )
2026-10-21 16:40:42 +08:00
ssongliu
c695a2a408
fix(firewall): prepare access whitelist before startup ( #14114 )
2026-10-16 17:27:48 +08:00
ssongliu
690cb48280
feat(vllm): refine monitor snapshots and historical request counts ( #14109 )
2026-10-16 13:36:29 +08:00