COMMITS
/ tools/server/server.cpp March 31, 2026
A
common : move up common_init() and fix Windows UTF-8 logs (#21176)
Adrien Gallouët committed
March 27, 2026
X
server: add built-in tools backend support (#20898)
Xuan-Son Nguyen committed
March 22, 2026
X
server: allow router to report child instances sleep status (#20849)
Xuan-Son Nguyen committed
March 6, 2026
A
webui: Agentic Loop + MCP Client with support for Tools, Resources and Prompts (#18655)
Aleksander Grygier committed
March 4, 2026
S
Fix locale-dependent float printing in GGUF metadata (#17331)
SamareshSingh committed
February 27, 2026
January 21, 2026
손
server: /v1/responses (partial) (#18486)
손희준 committed
January 5, 2026
V
server : fix router child env in containerized environments (#18562)
Vladislav Sayapin committed
December 22, 2025
X
server: prevent data race from HTTP threads (#18263)
Xuan-Son Nguyen committed
December 21, 2025
X
server: add auto-sleep after N seconds of idle (#18228)
Xuan-Son Nguyen committed
December 17, 2025
P
server: (webui) add --webui-config (#18028)
Pascal committed
X
server: (router) allow child process to report status via stdout (#18110)
Xuan-Son Nguyen committed
December 16, 2025
Y
server: fix crash when batch > ubatch with embeddings (#17912)
yifant-code committed
X
arg: clarify auto kvu/np being set on server (#17997)
Xuan-Son Nguyen committed
December 2, 2025
X
server: add --media-path for local media files (#17697)
Xuan-Son Nguyen committed
C
Server: Change Invalid Schema from Server Error (500) to User Error (400) (#17572)
Chad Voegele committed
December 1, 2025
X
server: introduce API for serving / loading / unloading multiple models (#17470)
Xuan-Son Nguyen committed
November 29, 2025
X
server: move server-context to its own cpp|h (#17595)
Xuan-Son Nguyen committed
November 28, 2025
F
server : add Anthropic Messages API support (#17570)
Fredrik Hultin committed
November 24, 2025
X
server: split server.cpp code into server/common/task/queue (#17362)
Xuan-Son Nguyen committed
November 17, 2025
X
server: split HTTP into its own interface (#17216)
Xuan-Son Nguyen committed
November 16, 2025
G
server : handle context overflow during decode (#17267)
Georgi Gerganov committed
November 14, 2025
X
mtmd: add mtmd_log_set (#17268)
Xuan-Son Nguyen committed
G
server : fix "can batch with" bug (#17263)
Georgi Gerganov committed
November 13, 2025
X
server: fixing naming conflict res_error (#17243)
Xuan-Son Nguyen committed
November 12, 2025
X
server: (refactor) implement generator-based API for task results (#17174)
Xuan-Son Nguyen committed
X
server: move res_error/res_ok to static function (#17167)
Xuan-Son Nguyen committed
November 9, 2025
G
server : handle failures to restore host cache (#17078)
Georgi Gerganov committed
November 8, 2025
A
November 7, 2025
G
server : print the samplers chain for each request (#17070)
Georgi Gerganov committed
November 6, 2025
G
server : disable checkpoints with mtmd (#17045)
Georgi Gerganov committed
November 5, 2025
G
server : do not default to multiple slots with speculative decoding (#17017)
Georgi Gerganov committed
November 4, 2025
G
server : do context shift only while generating (#17000)
Georgi Gerganov committed
November 3, 2025
G
server : add props.model_alias (#16943)
Georgi Gerganov committed
X
mtmd: add --image-min/max-tokens (#16921)
Xuan-Son Nguyen committed
November 2, 2025
G
clip : use FA (#16837)
Georgi Gerganov committed
G
server : support unified cache across slots (#16736)
Georgi Gerganov committed
October 31, 2025
G
server : don't print user inputs to console (#16871)
Georgi Gerganov committed
D
server : fix typos in server.cpp comments [no ci] (#16883)
Daniel Bevenius committed
October 30, 2025
G
server : remove n_past (#16818)
Georgi Gerganov committed
October 28, 2025
G
memory : remove KV cache size padding (#16812)
Georgi Gerganov committed
October 23, 2025
J
server: add memory breakdown print (#16740)
Johannes Gäßler committed
M
server : send partial stop string when <EOG> is reached (#15007)
matteo committed
October 15, 2025
G
server : fix img token logs (#16595)
Georgi Gerganov committed
G
server : fix mtmd checkpoints (#16591)
Georgi Gerganov committed
October 14, 2025
G
server : dynamic token limit for prompt cache (#16560)
Georgi Gerganov committed
October 11, 2025
Y
server / ranking : add sorting and management of top_n (#16403)
Yann Follet committed
October 10, 2025
G
server : fix division by zero when reporting stats (#16501)
Georgi Gerganov committed