Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

opencl: add Adreno xmem SDPA path (#26331)
yzyyzyhhh committed 2 months ago
4acf4a4
ci : move more jobs to ccache-buckets (#28375)
Sigbjørn Skjæret committed 2 months ago
8b4b355
llama.cpp : bump version to 0.4.0 (#28386)
Georgi Gerganov committed 2 months ago
5266f24
sync : ggml (#28379)
Georgi Gerganov committed 2 months ago
64a155d
model, mtmd: fix gemma4 vision handling (#28335)
Xuan-Son Nguyen committed 2 months ago
163a407
8f83678
86b351f
d509cb1
4cbe8b0
ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (#28177)
Adrien Gallouët committed 2 months ago
24f5bf8
a529af9
vendor: update BoringSSL to 0.20260903.0 (#28354)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 2 months ago
38521ec
ci : disable failing openvino tests (#28347)
Ravi Panchumarthy committed 2 months ago
0ef4d56
common : make build info output stream configurable (#28322)
Adrien Gallouët committed 2 months ago
c390d0a
832fd6f
src : add n_expert_used_max function (#28323)
Daniel Bevenius committed 2 months ago
9a4843c
f9f09f0
d230ddd
tune MMVQ to MMQ crossover for SM87 (#28285)
kbenkhaled committed 2 months ago
8c1a251
snapdragon: ci updates to use new run script (#28293)
Max Krasnyansky committed 2 months ago
d30500b
e107984
server : use pytest-xdist for server tests (#28298)
Daniel Bevenius committed 2 months ago
42f0225
mtmd: propagate const to preproc class (#28310)
Xuan-Son Nguyen committed 2 months ago
de8656b