Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

68a521b
bec4772
spec : fix naming, spacing (#25410)
Georgi Gerganov committed 4 months ago
c198af4
CUDA: Fuse MMVQ post-scale for NVFP4 (#24481)
Oliver Simons committed 4 months ago
3899b39
server: enforce prompt cache RAM limit (#25070)
Thiago Padilha committed 4 months ago
6c487e2
c1a411f
llama: fix quantized kv-cache for dsv4 (#25202)
Aman Gupta committed 4 months ago
024c46a
108f186
[SYCL] support op col2im_1d (#25264)
Neo Zhang committed 4 months ago
47e1de7
d209086
9e5ef0d
3d4cbdf
ggml : make ggml_time_init idempotent (#24422)
An Long committed 4 months ago
1a7c25b
f36e5c3
CUDA: remove -sm row, refactor cuBLAS (#24216)
Johannes Gäßler committed 4 months ago
74976e1
server: temporary skip model downloading API test (#25355)
Xuan-Son Nguyen committed 4 months ago
bfdf581
20a04b2