Commit Graph

  • 3567b7df08 Update image in README.md for web UI section Benson Wong 2025-11-08 15:29:37 -08:00
  • 38738525c9 config.example.yaml: add modeline for schema validation Benson Wong 2025-11-08 15:08:55 -08:00
  • c0fc858193 Add configuration file JSON schema (#393) Benson Wong 2025-11-08 15:04:14 -08:00
  • b429349e8a add /ui/ to wol-proxy polling (#388) Benson Wong 2025-11-08 14:16:12 -08:00
  • eab2efd7b5 feat: improve llama.cpp base image tag for cpu (#391) Ryan Steed 2025-11-08 17:56:49 +00:00
  • 6aedbe121a cmd/wol-proxy: show a loading page for / (#381) Benson Wong 2025-11-03 22:37:06 -05:00
  • b24467ab89 fix: update containerfile user/group management commands (#379) Ryan Steed 2025-11-03 22:17:40 +00:00
  • 12b69fb718 proxy: recover from panic in Process.statusUpdate (#378) v172 Benson Wong 2025-11-03 08:30:09 -05:00
  • f91a8b2462 refactor: update Containerfile to support non-root user execution and improve security (#368) Ryan Steed 2025-11-01 00:01:04 +00:00
  • a89b803d4a Stream loading state when swapping models (#371) v171 Benson Wong 2025-10-29 00:09:39 -07:00
  • f852689104 proxy: add panic recovery to Process.ProxyRequest (#363) v170 Benson Wong 2025-10-25 20:40:05 -07:00
  • e250e71e59 Include metrics from upstream chat requests (#361) v169 Benson Wong 2025-10-25 17:38:18 -07:00
  • d18dc26d01 cmd/wol-proxy: tweak logs to show what is causing wake ups (#356) Benson Wong 2025-10-25 11:04:31 -07:00
  • 8357714421 ui: fix avg token/sec calculation on models page (#357) v168 Benson Wong 2025-10-23 22:22:24 -07:00
  • c07179d6e2 cmd/wol-proxy: add wol-proxy (#352) v167 Benson Wong 2025-10-20 20:55:02 -07:00
  • 7ff50631e0 Update README for setup instructions clarity [skip ci] Benson Wong 2025-10-19 14:55:23 -07:00
  • 9fc0431531 Clean up and Documentation (#347) [skip ci] Benson Wong 2025-10-19 14:53:13 -07:00
  • 6516532568 Add optional TLS support (#340) v166 David Wen Riccardi-Zhu 2025-10-16 02:29:02 +00:00
  • d58a8b85bf Refactor to use httputil.ReverseProxy (#342) David Wen Riccardi-Zhu 2025-10-13 23:47:04 +00:00
  • caf9e98b1e Fix race conditions in proxy.Process (#349) Benson Wong 2025-10-13 16:42:49 -07:00
  • 539278343b ui: tweak vertical space for mobile (#343) v165 Benson Wong 2025-10-10 10:05:36 -07:00
  • 00b738cd0f Add Macro-In-Macro Support (#337) v164 Benson Wong 2025-10-06 22:57:15 -07:00
  • 70930e4e91 proxy: add support for user defined metadata in model configs (#333) v163 Benson Wong 2025-10-04 19:56:41 -07:00
  • 1f6179110c proxy/config: add model level macros (#330) Benson Wong 2025-09-28 23:32:52 -07:00
  • 216c40b951 proxy/config: create config package and migrate configuration (#329) Benson Wong 2025-09-28 16:50:06 -07:00
  • 9e3d491c85 proxyToUpstream: add redirect with trailing slash to upstream endpoint (#322) v162 Benson Wong 2025-09-25 16:43:00 -07:00
  • 1a84926505 proxy: add unload of single model (#318) v161 Benson Wong 2025-09-24 20:53:48 -07:00
  • fc3bb716df UI styling / code improvements (#307) v160 Oleg Shulyakov 2025-09-19 20:47:17 +03:00
  • c36986fef6 upstream handler support for model names with forward slash (#298) v159 Benson Wong 2025-09-13 13:37:03 -07:00
  • 558801db1a Fix nginx proxy buffering for streaming endpoints (#295) Artur Podsiadły 2025-09-10 01:07:46 +02:00
  • b21dee27c1 Fix #288 Vite hot module reloading creating multiple SSE connections (#290) Benson Wong 2025-09-07 21:48:58 -07:00
  • f58c8c8ec5 Support llama.cpp's cache_n in timings info (#287) v158 Benson Wong 2025-09-06 13:58:02 -07:00
  • 954e2dee73 Remove cmdStart from README [skip ci] Benson Wong 2025-09-04 11:57:28 -07:00
  • a533aec736 small tweak to example config v157 Benson Wong 2025-09-01 21:26:58 -07:00
  • 97b17fc47d Add ${MODEL_ID} macro (#226) Brett Profitt 2025-09-02 00:21:37 -04:00
  • 2457840698 Update README.md [skip ci] Benson Wong 2025-08-28 23:44:37 -07:00
  • 7f55494151 Update README.md [skip ci] Benson Wong 2025-08-28 22:47:28 -07:00
  • 831a90d3b0 Add different timeout scenarios to Process.checkHealthEndpoint #276 (#278) v156 Benson Wong 2025-08-28 22:03:14 -07:00
  • 977f1856bb add /completion endpoint (#275) Yandrik 2025-08-29 06:41:02 +02:00
  • 52b329f7bc Fix #277 race condition in ProcessGroup.ProxyRequest when swap=true Benson Wong 2025-08-28 21:38:36 -07:00
  • 57803fd3aa Support llama-server's /infill endpoint (#272) v155 Benson Wong 2025-08-27 08:36:05 -07:00
  • c55d0cc842 Add docs for model.concurrencyLimit #263 [skip ci] Benson Wong 2025-08-22 16:08:37 -07:00
  • 7acbaf4712 Add connection status indicator in UI (#260) v154 Benson Wong 2025-08-20 13:58:24 -07:00
  • fcc5ad135a UI: Allow editing of title (#246) v153 Benson Wong 2025-08-17 09:42:06 -07:00
  • 305e5a0031 improve example config [skip ci] Benson Wong 2025-08-17 09:19:04 -07:00
  • 04fc67354a Improve Activity event handling in the UI (#254) v152 Benson Wong 2025-08-15 21:44:08 -07:00
  • 4662cf7699 add 'unconfirmed bug' as default label in bug-report.md Benson Wong 2025-08-15 15:38:12 -07:00
  • 5dc6b3e6d9 Add barebones but working implementation of model preload (#209, #235) v151 Benson Wong 2025-08-14 10:27:28 -07:00
  • 74c69f39ef Add prompt processing metrics (#250) Benson Wong 2025-08-14 10:02:16 -07:00
  • a186318892 Update Readme, Add screenshot for Activities page [skip ci] Benson Wong 2025-08-08 13:39:46 -07:00
  • c4e4d5e1e9 Update Readme UI Screenshot [skip ci] Benson Wong 2025-08-08 13:33:47 -07:00
  • 7985e94ba4 add tokens processed to ui models page v150 Benson Wong 2025-08-08 11:05:36 -07:00
  • 74556c3a36 Update bug-report.md [skip ci] Benson Wong 2025-08-08 09:52:05 -07:00
  • 5c381e4b30 Add gofmt linting to ci Benson Wong 2025-08-07 20:19:56 -07:00
  • 10569ed546 Fix model alias usage in upstream path (#230) Benson Wong 2025-08-07 20:16:56 -07:00
  • 5b10b3c23f UI Tweaks (#228) Benson Wong 2025-08-07 11:07:03 -07:00
  • 45ea792a3a Fix UI panel not saving position correctly v149 Benson Wong 2025-08-06 14:02:22 -07:00
  • 1bc2802353 fix panels not saving sizing state Benson Wong 2025-08-06 14:00:21 -07:00
  • 701476c0c4 Update README.md - remove contributor block [skip ci] Benson Wong 2025-08-06 11:11:47 -07:00
  • 5c63e0066c return models sorted by id in /v1/models (#222) Ben Greene 2025-08-06 12:04:52 -05:00
  • 8be5073c51 Fix typo (#223) [skip ci] Martin Garton 2025-08-06 18:02:38 +01:00
  • 6307bd3205 Add support for building Linux ARM64 binary in Makefile (#221) Aaron Ang 2025-08-05 16:26:06 -07:00
  • 558a72de17 UI Improvements (#219) v148 Benson Wong 2025-08-03 17:49:13 -07:00
  • dc42cf366d Add config monitor support for k8s configmap. (#217) Leoyzen 2025-08-03 23:05:48 +08:00
  • ba0a81937a Update README.md (#216) Ryein Goddard 2025-08-01 19:48:09 -07:00
  • 574fdfabb4 UI improvements (#213) v147 Benson Wong 2025-07-31 11:59:21 -07:00
  • 5172cb2e12 Update docs in Readme [skip ci] Benson Wong 2025-07-30 11:51:14 -07:00
  • 5672cb03fd Update github actions for notifying homebrew build (#212) v146 Benson Wong 2025-07-30 11:29:03 -07:00
  • 0f583163f7 add /health (#211) v145 Benson Wong 2025-07-30 10:37:10 -07:00
  • 7905fa9ea3 Update trigger-homebrew-update.yml [skip ci] Benson Wong 2025-07-30 10:13:49 -07:00
  • bbaf172956 add trigger to rebuild homebrew formula (#210) Ian Sebastian Mathew 2025-07-30 22:42:21 +05:30
  • fd50932dbc Decouple MetricsMiddleware from downstream handlers (#206) v144 Benson Wong 2025-07-27 10:36:06 -07:00
  • 8c693e7fcf Add endpoint aliases for reranking models (#201) v143 Gaël James 2025-07-24 17:32:47 +02:00
  • 8f2af26a41 fix stats on model page v142 Benson Wong 2025-07-23 13:57:33 -07:00
  • 01d4838fb3 Fix token metrics parsing (#199) v141 Benson Wong 2025-07-22 23:10:14 -07:00
  • accd65294b add contributors to README [skip ci] Benson Wong 2025-07-21 23:16:48 -07:00
  • 7472a25864 Update README.md [skip ci] Benson Wong 2025-07-21 23:08:19 -07:00
  • cce0bc6aa1 add guard to ensure ls-real-model-name is set in context v140 Benson Wong 2025-07-21 22:59:41 -07:00
  • 36e25125e8 UI tidy [skip ci] Benson Wong 2025-07-21 22:47:55 -07:00
  • 9a54273d15 Update UI with new Activity event stream from #195 Benson Wong 2025-07-21 22:42:30 -07:00
  • 87dce5f8f6 Add metrics logging for chat completion requests (#195) g2mt 2025-07-21 22:19:55 -07:00
  • 307e619521 remove old eventsources from UI Benson Wong 2025-07-19 15:36:40 -07:00
  • 6299c1b874 Fix High CPU (#189) v139 Benson Wong 2025-07-15 18:04:30 -07:00
  • a906cd459b Strip comments before macro expansion in config (#193) v138 Yathi 2025-07-15 10:14:16 -07:00
  • 78b2bc3dbc add toggle to hide/show unlisted models (#187) v137 Benson Wong 2025-07-02 16:14:20 -07:00
  • 6a058e4191 Change fsnotify to watch config directory instead of file v136 Benson Wong 2025-07-02 10:22:39 -07:00
  • 1921e570d7 Add Event Bus (#184) v135 Benson Wong 2025-07-01 22:17:35 -07:00
  • c867a6c9a2 Add name and description to v1/models list (#179) v134 Benson Wong 2025-06-30 23:02:44 -07:00
  • 3bd1b23ce0 fix config hot-reload on k8s (#181) Leoyzen 2025-06-28 02:49:31 +08:00
  • 10606abf89 fix config hot-reload on macos (#180) v133 srevn 2025-06-26 19:20:50 +03:00
  • fefd14903d improve log display and add a small stats table in ui (#178) v132 Benson Wong 2025-06-25 12:27:49 -07:00
  • 717d64e336 update GUI image in README [skip ci] Benson Wong 2025-06-24 10:38:28 -07:00
  • 285191e655 Various UI improvements (#176) v131 Benson Wong 2025-06-23 16:17:21 -07:00
  • 4236cec03a Add Filters to Model Configuration (#174) Benson Wong 2025-06-23 10:52:29 -07:00
  • 756193d0dd Load models in the UI without navigating the page (#173) v130 Alex O'Connell 2025-06-19 17:39:07 -04:00
  • a6b2e930d8 Update README.md [skip ci] Benson Wong 2025-06-18 11:47:08 -07:00
  • 9e02c22ff8 stopCmd should use same environment as p.cmd.Env (#171, #172) v129 Benson Wong 2025-06-18 11:36:59 -07:00
  • 0bdbf2fdc1 fix more goreleaser deprecation warnings [skip ci] Benson Wong 2025-06-18 11:15:12 -07:00
  • 49035e2e8e Append custom env vars instead of replace in Process (#171) v128 Benson Wong 2025-06-18 11:09:13 -07:00
  • 9963ae18bf fix? deprecation warning in .goreleaser.yaml [skip-ci] Benson Wong 2025-06-18 07:49:33 -07:00