mintyleaf 0d6c3a7d57 feat: include tokens usage for streamed output (#4282) ... Use pb.Reply instead of []byte with Reply.GetMessage() in llama grpc to get the proper usage data in reply streaming mode at the last [DONE] frame Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>		2024-11-28 14:47:56 +01:00
..
ctx	chore: get model also from query (#3716)	2024-10-02 20:20:50 +02:00
elements	feat(ui): move model detailed info to a modal (#4086)	2024-11-06 18:25:59 +01:00
endpoints	feat: include tokens usage for streamed output (#4282)	2024-11-28 14:47:56 +01:00
middleware	feat: add WebUI API token authorization (#4197)	2024-11-19 18:43:02 +01:00
routes	feat(silero): add Silero-vad backend (#4204)	2024-11-20 14:48:40 +01:00
static	feat(ui): move model detailed info to a modal (#4086)	2024-11-06 18:25:59 +01:00
views	feat: add WebUI API token authorization (#4197)	2024-11-19 18:43:02 +01:00
app.go	feat: allow to disable '/metrics' endpoints for local stats (#3945)	2024-10-23 15:34:32 +02:00
app_test.go	feat(backends): Drop bert.cpp (#4272)	2024-11-27 16:34:28 +01:00
explorer.go	feat(explorer): make possible to run sync in a separate process (#3224)	2024-08-12 19:25:44 +02:00
http_suite_test.go	fix: rename fiber entrypoint from http/api to http/app (#2096)	2024-04-21 22:39:28 +02:00
render.go	rf: centralize base64 image handling (#2595)	2024-06-24 08:34:36 +02:00