llama.cpp
server: refactor batch construction
#24843
Merged

server: refactor batch construction #24843

ngxson merged 15 commits into master from xsn/server_refactor_batch
ngxson
ngxson server: refactor batch construction
d5037c50
ngxson wip
6c5c5a29
github-actions github-actions added examples
github-actions github-actions added server
ngxson wip 2
2b2eed8f
ngxson wip 3
b786bb2e
ngxson wip 4
af583e3e
ngxson add abort_all_slots
d704c792
ngxson handle batch full more carefully
64ec03d1
ngxson fix assert
bf36838e
ngxson rm debug log
53763db7
ngxson Merge branch 'master' into xsn/server_refactor_batch
b28e3682
ngxson small nits
ea65a4b1
ngxson (debug) add timings
7486a397
ngxson debug: force llama_synchronize for accurate timings
a527509d
ngxson
ngxson commented on 2026-06-20
ngxson
ngxson ngxson marked this pull request as ready for review 30 days ago
ngxson ngxson requested a review 30 days ago
ngxson ngxson requested a review from ggerganov ggerganov 30 days ago
ggerganov ggerganov assigned ggerganov ggerganov 30 days ago
angt
ngxson
ggerganov
ggerganov commented on 2026-06-21
ngxson
ngxson address comments
d3741451
ggerganov
ggerganov approved these changes on 2026-06-21
ServeurpersoCom
ServeurpersoCom approved these changes on 2026-06-21
ngxson disable DEBUG_TIMINGS
7ac864bf
ngxson ngxson merged bddfd2b1 into master 29 days ago

Login to write a write a comment.

Login via GitHub

Assignees
Labels
Milestone