Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

a6b83d4
opencl: add F32-to-I32 ARGMAX (#30897)
kurquhar committed 28 days ago
c7fc509
a37cc46
7775ffb
llama: create new fused op for QSA mask (#30640)
Aman Gupta committed 29 days ago
d454a20
sycl: q8 fast dequant (#30775)
92es committed 29 days ago
0756e83
9febe63
ggml-opencl : add IM2COL_3D support (#30895)
kurquhar committed 29 days ago
9b56ccf
mtmd: add state object for mtmd_gen (#30902)
Xuan-Son Nguyen committed 29 days ago
0a1ef30
vendor: update BoringSSL to 0.20261020.0 (#30889)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 29 days ago
f849095
llama : optimize vocabulary loading (#30679)
Evgen Mykhailenko committed 29 days ago
824eaec
0efe8e4
8baabd5
Sycl iq3 crash fix (#30604)
Anant Shrivastava committed 29 days ago
493253f
339f324
server : add POST /tts endpoint for TTS models (#26603)
Xuan-Son Nguyen committed 1 month ago
5c0b49a
server: add realtime transcription API (#30636)
Xuan-Son Nguyen committed 1 month ago
1242be6
model : support Nemotron-3(.5)-Embed (#30877)
Takamichi Ohara committed 1 month ago
52ffa02
qwen: reshape output to 2d instead of 3d (#30823)
Aman Gupta committed 1 month ago
839a572
ead9f32