llama.cpp
server : implement prompt processing progress report in stream mode
#15827

Merged

server : implement prompt processing progress report in stream mode #15827

ngxson merged 7 commits into master from xsn/server_progress_api

server : implement `return_progress`

29f1d50e

github-actions added examples

github-actions added server

add timings.cache_n

4404ad86

add progress.time_ms

e166a550

add test

f4213ccd

github-actions added python

fix test for chat/completions

ebcef910

ngxson marked this pull request as ready for review 103 days ago

readme: add docs on timings

b6ac24c6

ngxson requested a review from

ggerganov 103 days ago

ngxson requested a review from

allozaur 103 days ago

ggerganov approved these changes on 2025-09-06

ggerganov commented on 2025-09-06

use ggml_time_us

053dc6b3

ngxson merged 61bdfd52 into master 103 days ago

ngxson deleted the xsn/server_progress_api branch 74 days ago

Reviewers

ggerganov

allozaur

Assignees

No one assigned

Labels

examples python server

Milestone

No milestone