mintyleaf 2bc4b56a79

feat: stream tokens usage (#4415) ...

* 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

* Fix 'hang' on empty message from the start

Seems like that empty message marker trick was unnecessary

---------

Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

2024-12-18 09:48:50 +01:00

..

backend_suite_test.go

feat: extract output with regexes from LLMs (#3491)

2024-09-13 13:27:36 +02:00

embeddings.go

chore(refactor): drop unnecessary code in loader (#4096)

2024-11-08 21:54:25 +01:00

image.go

chore(refactor): drop unnecessary code in loader (#4096)

2024-11-08 21:54:25 +01:00

llm_test.go

feat: extract output with regexes from LLMs (#3491)

2024-09-13 13:27:36 +02:00

llm.go

feat: stream tokens usage (#4415)

2024-12-18 09:48:50 +01:00

options.go

feat(llama.cpp): expose cache_type_k and cache_type_v for quant of kv cache (#4329)

2024-12-06 10:23:59 +01:00

rerank.go

chore(refactor): drop unnecessary code in loader (#4096)

2024-11-08 21:54:25 +01:00

soundgeneration.go

chore(refactor): drop unnecessary code in loader (#4096)

2024-11-08 21:54:25 +01:00

stores.go

chore(refactor): drop unnecessary code in loader (#4096)

2024-11-08 21:54:25 +01:00

token_metrics.go

chore(refactor): drop unnecessary code in loader (#4096)

2024-11-08 21:54:25 +01:00

tokenize.go

chore(refactor): drop unnecessary code in loader (#4096)

2024-11-08 21:54:25 +01:00

transcript.go

chore(refactor): drop unnecessary code in loader (#4096)

2024-11-08 21:54:25 +01:00

tts.go

chore(refactor): drop unnecessary code in loader (#4096)

2024-11-08 21:54:25 +01:00