Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

vendor : update cpp-httplib to 0.54.0 (#27919)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 2 months ago
dc7aecf
rpc : fix pre-rdma macOS versions (#27815)
Ryan C committed 2 months ago
2bf0415
metal : add fa-vec tunings for M2 (#27940)
codemonkey committed 2 months ago
c589f0e
metal : assert shared memory padding (#27951)
Georgi Gerganov committed 2 months ago
3173a56
17252c7
sycl: make --fit respect --fit-target better (#27629)
Nick Farrell committed 2 months ago
cc83d7b
metal : add fa-vec tunings for M1 Max (#27932)
Jhen-Jie Hong committed 2 months ago
5ea1b12
77f132c
snapdragon: python SDK setup (Windows) (#27903)
kurquhar committed 2 months ago
d7bd3bf
bench: add --tensor-read-lazy (#27881)
Xuan-Son Nguyen committed 2 months ago
50f068f
model: qwen4exp: reduce number of graph splits (#27880)
Xuan-Son Nguyen committed 2 months ago
6fe7498
a43c398
context : disable non-fused GDN and LID ops (#27877)
Georgi Gerganov committed 2 months ago
8663224
metal : add fa-vec tunings for M4 (#27875)
Strongtut committed 2 months ago
f5e85d4
b19cbe9
sycl: use TILE for quantized KV decode on BMG (#26689)
Ozymandias_EBON committed 2 months ago
d077b4c
8963a9b
metal : add fa-vec tunings for M4 Pro (#27824)
Brad Smith committed 2 months ago
6d6b697
4e97ac8