Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

opencl: q8_0 gemv precision improvement (#24923)
Shawn Gu committed 5 months ago
23ee879
server : Add id to tool call responses api (#24882)
Matt Thompson committed 5 months ago
dec5ca5
9c0ac88
server: refactor/generalize input file schema (#24299)
Xuan-Son Nguyen committed 5 months ago
6ee0f65
f8cc15f
server: refactor batch construction (#24843)
Xuan-Son Nguyen committed 5 months ago
bddfd2b
mtmd: fix mtmd_get_memory_usage (#24867)
Xuan-Son Nguyen committed 5 months ago
0d135df
jinja : implement call statement (#24847)
Sigbjørn Skjæret committed 5 months ago
bf53382
mtmd: add load progress callback (#24865)
Xuan-Son Nguyen committed 5 months ago
2f89acc
server: add "verbose" field to schema (#24864)
Xuan-Son Nguyen committed 5 months ago
bfa3219
minor : clean-up whitespaces (#24862)
Georgi Gerganov committed 5 months ago
8a118ee
spec : Support Step3.5/3.7 flash mtp3 (#24340)
YiChen Lv committed 5 months ago
d789527
063d9c1
4a80943
84de01a
arg: try fixing test-args-parser randomly fails (#24826)
Xuan-Son Nguyen committed 5 months ago
75f460a
8452824
67e9fd3
796f41b