LLM inference in C/C++
C++ ggml
Commits on master
ci : fix Models Backend Check by shortening the hrm_text fixture (#29744)
3b3d022 Pascal committed 1 month ago
ggml : add BF16 unary, GLU, binary and scale ops (CPU, CUDA) (#29675)
2090f60 Aman Gupta committed 1 month ago
model-conversion : add --add-bos to run org model script (#29558)
8df332d Daniel Bevenius committed 1 month ago
ui : model id grammar for sidecars, quants and capability parsing (#27946)
f653250 Aleksander Grygier committed 1 month ago
ui : type-safe API types, fetch helpers and download-ready models store plumbing (#29582)
fa2bde5 Aleksander Grygier committed 1 month ago
openvino: serve GET_ROWS on a weight view from the base Constant (#28381)
25747b0 Pascal committed 1 month ago
ci : fix Fusion / metal by adding glm5-next to MTL.csv (#29712)
db00347 Pascal committed 1 month ago
SYCL: reduce tensor allreduce sync with pinned host buffers (#29604)
2a53ace Captain-Tripps committed 1 month ago
vendor: update BoringSSL to 0.20260929.0 (#29669)
931351e Alessandro de Oliveira Faria (A.K.A.CABELO) committed 1 month ago
gguf : reject tensor size that wraps after padding (#26979)
a6ea155 Xiang Chen committed 1 month ago
CUDA: bitonic argsort handles rows wider than one block (#28957)
6a2743f Pascal committed 1 month ago
ggml-cuda: HIP: optimize packed byte subtraction (`__vsubss4` -> `__vsub4`) (#29478)
748d422 thelittlefireman committed 1 month ago
opencl: fix get_tensor for q5_K adreno gemm_nonshuffle kernel (#29555)
6dbbac4 lhez committed 1 month ago
vulkan : Load F32 A matrix 2 at a time when its 2-aligned (#29254)
83dd71f Matt Corallo committed 1 month ago