Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

DeepseekV4: fix seq_rm (#25588)
Aman Gupta committed 4 months ago
7f575c3
vulkan/cpu: Support f16 as SET_ROWS src. (#25432)
Jeff Bolz committed 4 months ago
7cbd610
tokenize : align usage by using common args (#25516)
Adrien Gallouët committed 4 months ago
8ff8c42
kleidiai : add SME2 f32 kernel (#24414)
Charles Xu committed 4 months ago
47c7869
cb489bc
arg: Flush log before exiting after usage() (#25504)
Christian Kastner committed 4 months ago
ec0dbef
c1063ac
metal : add Q2_0 support (#25419)
Pasha Khosravi committed 4 months ago
14d3ba4
CUDA: refactor MMQ kernel configuration (#24127)
Johannes Gäßler committed 4 months ago
6eddde0
spec: add Minimax2 eagle3 support
Adrian committed 4 months ago
259ae1d
readme : add link to maintainer PRs (#25621)
Georgi Gerganov committed 4 months ago
4193ea6
tests: Harmonize header use (#25616)
Christian Kastner committed 4 months ago
f4253ef
gguf : add tensor shape accessor (#24405)
QuintinShaw committed 4 months ago
ad8d821
sycl: add fused top-k MoE (#25217)
Frosty40 committed 4 months ago
efb3036
sycl: add Q2_K to DMMV reorder path (#25064)
Todd Malsbary committed 4 months ago
e474bba
vendor : update cpp-httplib to 0.50.1 (#25576)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 4 months ago
3455882
0c4fa7a