llama.cpp
server : refactor
#5882
Merged

server : refactor #5882

ggerganov merged 26 commits into master from gg/refactor-server
ggerganov
ggerganov server : refactoring (wip)
f4e6e7e6
ggerganov server : remove llava/clip objects from build
ef7eb339
ggerganov server : fix empty prompt handling + all slots idle logic
134f5fec
ggerganov server : normalize id vars
ad1d746c
ggerganov server : code style
fef64c58
ggerganov server : simplify model chat template validation
b1b3ba88
phymbert
ggerganov server : code style
f4800d54
ggerganov server : minor
7635b13a
ggerganov llama : llama_chat_apply_template support null buf
f84809b7
ggerganov
ggerganov server : do not process embedding requests when disabled
22ae1a62
ggerganov server : reorganize structs and enums + naming fixes
cb3ce0bf
ggerganov server : merge oai.hpp in utils.hpp
4a2d5f63
ggerganov server : refactor system prompt update at start
61b63705
chigkim
phymbert
ggerganov server : disable cached prompts with self-extend
aef02b11
ggerganov
ggerganov server : do not process more than n_batch tokens per iter
bfb121fd
phymbert server: tests: embeddings use a real embeddings model (#5908)
79ef3c05
ggerganov server, tests : bump batch to fit 1 embedding prompt
36e12f8f
ggerganov
phymbert
ggerganov
phymbert
phymbert server: tests: embeddings fix build type Debug is randomly failing (#…
59850f18
phymbert
phymbert approved these changes on 2024-03-06
phymbert server: tests: embeddings, no need to wait for server idle as it can …
3166ccf5
phymbert server: refactor: clean up http code (#5912)
c50a5100
ggerganov ggerganov marked this pull request as ready for review 1 year ago
ggerganov server : avoid n_available var
c53d84ec
cebtenzzre
cebtenzzre commented on 2024-03-06
phymbert server: refactor: better http codes
9c8d3c8a
ngxson
ngxson commented on 2024-03-06
ngxson
ngxson commented on 2024-03-06
ngxson
ngxson commented on 2024-03-06
ggerganov server : simplify json parsing + add comment about t_last
fd74b5ea
ggerganov server : rename server structs
234ab58a
ggerganov server : allow to override FQDN in tests
818d898f
ggerganov server : add comments
87a4a105
ggerganov ggerganov merged 2002bc96 into master 1 year ago
ggerganov ggerganov deleted the gg/refactor-server branch 1 year ago
phymbert
phymbert commented on 2024-03-07
ggerganov
sorasoras
whoreson
Kreijstal
Dampfinchen
phymbert
cartertemm
GrigoryEvko

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone