This website requires JavaScript.
5938dbee8f
Push unified docker images on scheduled runs (#694 )
Bryan Gahagan
2026-04-22 23:46:51 -04:00
66639e83f7
proxy: replace fsnotify with stat-poll watcher and add SIGHUP reload (#685 )
v205
Benson Wong
2026-04-21 23:21:48 -07:00
625b296720
docker/unified: add uv via pip install (#681 )
Benson Wong and Claude
2026-04-20 20:55:51 -07:00
231e62291c
proxy: fix matrix race and process stop bug (#677 )
v204
Benson Wong
2026-04-20 00:21:11 -07:00
57ac666598
.github/workflows: tweak push ghcr conditional (#676 )
Benson Wong
2026-04-19 13:56:26 -07:00
69728301f5
.github/workflows: add toggle for pushing unified images to github (#672 )
Benson Wong
2026-04-19 10:10:48 -07:00
c176fa70f1
docker/unified: add spirv-headers to fix vulkan build (#669 )
Benson Wong
2026-04-18 12:18:10 -07:00
5e3c646829
proxy: compress captures with zstd (#668 )
v203
Benson Wong
2026-04-17 23:29:37 -07:00
c3f0d43e6e
proxy: fix race conditions during swap (#667 )
Benson Wong
2026-04-17 21:23:17 -07:00
f6cf9f5844
proxy: Refactor tests (#660 )
Benson Wong
2026-04-16 22:47:42 -07:00
121fd93ad8
Makefile: restore linux arm64 targets
Benson Wong
2026-04-14 22:05:39 -07:00
17233e9278
docs: update configuration.md for matrix
v202
Benson Wong
2026-04-14 22:01:03 -07:00
4866d16c3e
README.md: update to use matrix instead of groups
Benson Wong
2026-04-14 21:57:49 -07:00
35193f82f1
proxy: add swap matrix with solver-based model swapping (#646 )
Benson Wong
2026-04-14 21:55:30 -07:00
40e39f7a86
ui-svelte: fix security issues (#649 )
Benson Wong
2026-04-12 16:21:31 -07:00
a9d840ffd7
proxy,proxy/config: restore timeouts to pre PR 619 (#648 )
v201
Benson Wong
2026-04-11 20:42:13 -07:00
7b2b82777f
docker/unified: derive rootless image from root container (#644 )
Benson Wong and Claude Sonnet 4.6
2026-04-10 22:59:54 -07:00
d87f0ce2c5
docker/unified: publish rootless image variant (#630 )
v200
Benson Wong
2026-04-07 03:05:53 -07:00
06bc6a614c
proxy: preserve wall-clock duration in metrics (#629 )
Leoy
2026-04-07 16:52:41 +08:00
a37b4866d8
proxy: add configurable HTTP timeouts for models and peers (#619 )
Ron M
2026-04-06 04:30:27 -07:00
981910d734
ci: validate config.example.yaml against config-schema.json (#627 )
Benson Wong and Claude
2026-04-05 15:17:57 +08:00
a185efe37e
docker: make CMAKE_CUDA_ARCHITECTURES configurable via build arg (#625 )
Benson Wong and Claude
2026-04-04 08:49:59 +08:00
1dd1aadf93
docker/unified: add ik_llama.cpp to CUDA container (#620 )
Benson Wong
2026-04-03 15:16:30 +08:00
955900972a
add /sdapi to list of supported endpoints
Benson Wong
2026-04-01 12:01:38 +08:00
c2c8cfaf81
docker/unified: build llama.cpp with static libraries (#616 )
Benson Wong
2026-04-01 03:38:07 +08:00
1e440770ea
ci: fix matrix exclude for scheduled docker workflow (#610 )
Benson Wong
2026-03-29 20:04:28 +09:00
c794273c83
docker/unified,.github: fix unified build (#606 )
Benson Wong
2026-03-27 10:31:12 +09:00
6574a52cbb
build(deps): bump picomatch from 4.0.3 to 4.0.4 in /ui-svelte (#605 )
dependabot[bot]
2026-03-26 22:28:24 +09:00
8fabc75634
docker/unified: vulkan build fixes (#600 )
v199
Benson Wong and Claude Opus 4.6
2026-03-25 23:26:13 +09:00
e5e7391b6d
.github,docker/unified: include vulkan build (#599 )
Benson Wong
2026-03-25 06:58:28 +09:00
2c282dccad
.github,docker/unified: improve caching and fix bugs (#598 )
Benson Wong
2026-03-23 22:24:40 +09:00
916d13f5bd
.github/workflows,docker/unified: add cuda based unified container (#597 )
Benson Wong
2026-03-22 21:11:54 +09:00
a3725e7d09
Update go.mod to 1.26.1 (#593 )
Benson Wong
2026-03-20 16:09:58 +09:00
15bd55d3a9
proxy, ui-svelte: add /sdapi/v1 endpoint support (#587 )
Benson Wong and Claude
2026-03-19 22:08:31 +09:00
c3c258a55d
proxy: fix metrics capture for v1/responses (#586 )
v198
Benson Wong
2026-03-13 16:50:12 -07:00
29a38fde0d
ui-svelte: upgrade to vite 8 (#585 )
Benson Wong and Claude
2026-03-13 08:45:59 -07:00
d569681daa
Change model sorting to natural order (#582 )
tesuri
2026-03-12 23:49:34 +09:00
24efdb76b1
config: add macro support for name and description fields (#578 )
Benson Wong
2026-03-10 08:27:05 -07:00
cc77139ff8
proxy,proxy/config: add global TTL feature (#554 )
v197
Benson Wong
2026-03-01 21:02:12 -08:00
390a35bf93
ui-svelte: add copy button to markdown code blocks (#537 )
Benson Wong and Claude
2026-03-01 09:48:56 -08:00
181f71ca11
.github,docker: add cuda13 architecture support (#551 )
pdscomp
2026-03-01 12:37:08 -05:00
49546e2cf2
ui: fix text size svg
v196
Benson Wong
2026-02-27 23:47:28 -08:00
2c078964f4
Update README with additional images
Benson Wong
2026-02-27 23:45:40 -08:00
175bb36fb1
Revise README description for clarity and detail
Benson Wong
2026-02-27 23:42:40 -08:00
aedb640471
Enhance web UI section in README
Benson Wong
2026-02-27 23:40:31 -08:00
2f377f6dc6
ui: add OGG audio format support to transcription playground (#544 )
Benson Wong
2026-02-26 19:48:19 -08:00
64e4c79fc3
ui: add Rerank tab to playground (#536 )
v195
Benson Wong
2026-02-21 21:59:14 -08:00
19fb5f35e9
proxy: implement setParamsByID filter (#535 )
v194
Benson Wong
2026-02-19 22:21:10 -08:00
b45102bde8
ui: smart auto-scroll in LogPanel (#530 )
v193
Benson Wong
2026-02-18 19:47:37 -08:00
1688bdd1e9
proxy, ui: add pending requests count to the main dashboard (#516 )
v192
Brian Mendonca
2026-02-16 09:41:15 -08:00
d33d51fa75
.coderabbit.yaml,AGENTS.md: small tweaks
v191
Benson Wong
2026-02-15 21:31:30 -08:00
e3bf065574
ui: persist playground state across route navigation (#525 )
Benson Wong
2026-02-15 21:30:52 -08:00
3e52144058
ui-svelte: incremental rendering of chat messages in the Playground (#520 )
Benson Wong
2026-02-15 11:00:44 -08:00
d5e52d7d00
build: disable provenance attestations in container builds (#523 )
Benson Wong
2026-02-14 10:23:08 -08:00
17e5263a76
.github/workflows: fix expired token in publishing images (#522 )
Benson Wong
2026-02-14 10:06:05 -08:00
8d6d949ec3
proxy: support timings for /infill from llama-server (#510 )
Benson Wong
2026-02-07 17:16:27 -08:00
4b4ee70154
proxy: support timings for /infill from llama-server
v190
Benson Wong
2026-02-07 16:54:02 -08:00
b5fde8eb6d
proxy,ui-svelte: add request/response capturing (#508 )
Benson Wong
2026-02-07 15:40:01 -08:00
7eef5defb8
docs: add stable-diffusion.cpp references (#506 )
Nuno
2026-02-05 05:20:39 +01:00
bc01e6f539
build: add stable-diffusion server to musa and vulkan container images (#504 )
v189
Benson Wong
2026-02-01 16:17:26 -08:00
0462e3dc3f
Reorganize UI controls and improve form interactions (#500 )
Benson Wong
2026-02-01 15:18:22 -08:00
7b20fc011b
Add path filters to CI workflows and create UI test workflow (#501 )
Benson Wong and Claude
2026-02-01 15:11:49 -08:00
20738f3623
proxy,ui-svelte: replace old UI with svelte+playground
v188
Benson Wong
2026-01-31 22:49:13 -08:00
cdea7d16bd
proxy/config: skip env macros in YAML comment lines (#496 )
Benson Wong
2026-01-30 20:10:29 -08:00
5de387dbf9
ui: fix node-tar vulnerability
v187
Benson Wong
2026-01-28 21:40:18 -08:00
6f8e7ccb57
.github/workflows: switch release.yml to build ui-svelte
Benson Wong
2026-01-28 21:39:06 -08:00
4384315b44
ui-svelte: add Svelte port of React UI (#487 )
Benson Wong
2026-01-28 21:37:29 -08:00
6439ab1515
ui: add peer:true in package-lock.json
v186
Benson Wong
2026-01-22 08:43:36 -08:00
f94226122c
build(deps-dev): bump tar from 7.5.3 to 7.5.6 in /ui (#477 )
dependabot[bot] and dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-01-21 22:55:02 -08:00
7493618fdc
Add count_tokens api proxying (#476 )
Ryan Voots
2026-01-20 12:34:42 -05:00
205efd40a1
proxy: extend /running endpoint with additional process data (#474 )
Benson Wong
2026-01-19 17:37:00 -08:00
14207f8492
ui: npm security update
Benson Wong
2026-01-18 21:56:32 -08:00
4e850c2834
config: refactor macro substitution in configuration (#470 )
Benson Wong
2026-01-18 21:52:34 -08:00
75fced579e
config: support macros in peer apiKey and filters (#469 )
v185
Benson Wong
2026-01-16 23:10:50 -08:00
b73f367f22
config-schema.json,config.example.yaml: Update examples and schema
v184
Benson Wong
2026-01-16 22:43:25 -08:00
8f2137c72b
config: support environment variable macros in apiKeys (#467 )
Benson Wong
2026-01-16 22:41:14 -08:00
124007cc98
config: add environment variable macros (#466 )
Benson Wong
2026-01-16 22:25:20 -08:00
eb5bfff0b0
proxy: unify filtering for local models and peers
Benson Wong
2026-01-15 18:59:43 -08:00
3edb180c08
ci: free up disk space before ROCm container build (#460 )
Benson Wong
2026-01-14 22:03:42 -08:00
66d555e625
Improve container build reliability (#457 )
Benson Wong
2026-01-10 22:14:33 -08:00
4f863fd9fc
CLAUDE.md: tweak instructions
Benson Wong
2026-01-09 21:42:06 -08:00
267c030457
ui: update react-router-dom to 7.12.0 (#456 )
v183
Benson Wong and Claude
2026-01-08 16:13:09 -08:00
c19309fe7e
CLAUDE.md: small instruction tweaks
Benson Wong
2026-01-07 21:34:23 -08:00
4413881b2d
proxy: actually add /v1/responses endpoint (#449 )
v182
Benson Wong
2026-01-01 13:35:45 -08:00
8df5e8563b
proxy: add /v1/responses and /v1/audio/voices endpoints (#448 )
v181
Benson Wong
2026-01-01 12:52:12 -08:00
7931212d3e
proxy: add v1/images/edits API endpoint (#447 )
Benson Wong
2026-01-01 12:43:06 -08:00
3dc36032fb
proxy: skip very slow tests in -short test mode (#446 )
Benson Wong
2025-12-31 14:08:56 -08:00
addb98646f
proxy: add support for basic authorization (#445 )
Benson Wong
2025-12-31 13:42:35 -08:00
37d74efc2d
proxy: add /v1/images/generations (#443 )
v180
Benson Wong
2025-12-30 21:04:58 -08:00
22e098ac8b
Add Peer Model Support (#438 )
v179
Benson Wong
2025-12-27 20:18:06 -08:00
9864f9f517
.coderabbit.yaml: disable annoying features
Benson Wong
2025-12-23 23:52:48 -08:00
53b32f3601
proxy: add API key support (#436 )
Benson Wong
2025-12-23 23:39:33 -08:00
565c44766d
config,proxy: add new configuration logToStdout (#432 )
v178
Benson Wong
2025-12-21 22:23:31 -08:00
e6a9e210ba
proxy: fix path bug in /logs/stream/{model_id} (#431 )
Benson Wong
2025-12-21 21:47:14 -08:00
d3f329f924
proxy: Improve logging performance and allow separate log streaming (#421 )
v177
Benson Wong
2025-12-18 21:49:25 -08:00
98879b38c1
docker: add /app to $PATH (#424 )
Benson Wong
2025-12-06 22:58:29 -08:00
7b3b0f5eae
move header images around [skip ci]
Benson Wong
2025-12-02 19:40:42 -08:00
021ccceef1
README: update hero image
Benson Wong
2025-12-02 19:37:03 -08:00
f03871c50a
Update README.md
Benson Wong
2025-12-02 19:03:01 -08:00
dc00d17abe
docs: add documentation for non-root container images and security considerations (#416 )
Ryan Steed
2025-12-02 16:52:26 +00:00