Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

76c956c
ui: CWD for agent (#26518)
Aleksander Grygier committed 3 months ago
2f56fc3
models : fix dflash wo_a reshape on load (#26577)
Georgi Gerganov committed 3 months ago
1c3c967
sync : ggml
Georgi Gerganov committed 3 months ago
2e17f69
ggml : bump version to 0.18.1 (ggml/1578)
Georgi Gerganov committed 3 months ago
15831f5
b5746d2
vulkan backend ops: implemented GATED_LINEAR_ATTN (#25601)
Pranav Uttarkar committed 3 months ago
f26efa0
vocab : validate plamo2 byte tokens (#26511)
Sigbjørn Skjæret committed 3 months ago
cf06ad7
model : allow reshape of tensors during load (#26531)
Georgi Gerganov committed 3 months ago
1269cb1
ci: fix vulkan llvmpipe runs (#26533)
Eve committed 3 months ago
22dc605
6c8dcaa
0ef6e55
vendor : update cpp-httplib to 0.52.0 (#26485)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 3 months ago
94bc47f
vendor : update BoringSSL to 0.20260803.0 (#26523)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 3 months ago
fe2adf0
model : support MTP in GLM-4.7-Flash (#24868)
jacekpoplawski committed 3 months ago
57c0921
server: add get_info tool (#26522)
Xuan-Son Nguyen committed 3 months ago
99111b1
vocab : validate default special token ids (#26506)
Sigbjørn Skjæret committed 3 months ago
e8e06f7
39eab74