Morph MORPH
SIGN IN SIGN UP
ggml-org / llama.cpp UNCLAIMED

LLM inference in C/C++

0 0 0 C++

COMMITS

master
March 29, 2026
N
[SYCL] Enhance build script to use half cores to build, avoid OS hang (#21093)
Neo Zhang committed
afe65aa
March 28, 2026
S
fix **/x glob matching (#21129)
Sigbjørn Skjæret committed
6509718
P
common/parser: fix handling of tool definition with missing properties key (#21128)
Piotr Wilkin (ilintar) committed
98ae0a0
S
common : add character class support to glob_match (#21111)
Sigbjørn Skjæret committed
3a14a54
B
WebUI: Replace illegal nested button elements (#21026)
BlueMöhre committed
9681897
A
common/json-schema: fix: handle non-capturing groups (?:...) in JSON schema pattern converter (#21124)
Adrien committed
e397d38
A
common : add reasoning_format = none support to gpt-oss (#21094)
Aldehir Rojas committed
e6f2ec0
G
server : fix processing of multiple back-to-back mtmd chunks (#21107)
Georgi Gerganov committed
edfb440
A
ci : gracefully shut down the server (#21110)
Adrien Gallouët committed
3d66da1
W
Document custom default webui preferences in server README (#19771)
Woof Dog committed
82b703f
A
webui: Conversation forking + branching improvements (#21021)
Aleksander Grygier committed
51a84ef
A
vendor : update cpp-httplib to 0.40.0 (#21100)
Adrien Gallouët committed
b0f0dd3
R
vulkan: add noncontiguous GLU support (#21081)
Ruben Ortlam committed
0eb4764
P
common/parser: fix reasoning whitespace bugs + extra parser tests (#21085)
Piotr Wilkin (ilintar) committed
1f5d15e
S
cli : add /glob command (#21084)
Sigbjørn Skjæret committed
c46758d
T
docker : fix and enable ARM64 image build (#20929)
Ts-sound committed
bf934f2
A
server : add custom socket options to disable SO_REUSEPORT (#21056)
Adrien Gallouët committed
5c1a7b8
March 27, 2026
A
common : inhibit lazy grammar sampler while reasoning is active (#20970)
Aldehir Rojas committed
59d8402
K
server: Introduce LLAMA_BUILD_WEBUI build flag to allow disabling the embedded web ui (#20158)
Kusha Gharahi committed
ff934e2
Y
hexagon: support for IQ4_NL and MXFP4 (#21018)
Yiwei Shao committed
ee051c1
A
webui: Improve Chat Messages initial scroll + auto-scroll logic + add lazy loading with transitions to content blocks (#20999)
Aleksander Grygier committed
e6f6770
A
server: remove the verbose_prompt parameter (#21059)
AN Long committed
48cda24
X
mtmd: add more sanity checks (#21047)
Xuan-Son Nguyen committed
871f1a2
X
server: add built-in tools backend support (#20898)
Xuan-Son Nguyen committed
20197b6
R
rpc : proper handling of data pointers to CPU buffers (#21030)
Radoslav Gerganov committed
ba38f3b
M
completion : session_tokens insert range in completion tool (no-op → correct) (#20917)
mtmcp committed
37f230d
M
completion : Fix segfault on model load failure (#21049)
mtmcp committed
a308e58
P
Send reasoning content back to the model across turns via the reasoning_content API field (#21036)
Pascal committed
d0fa2c9
R
metal : Fix dimension constraint violation in matmul2d descriptor (#21048)
ren committed
9bcb4ef
K
CANN: update docker images to 8.5.0 and improve CANN.md (#20801)
KokerZhou committed
6861f65