Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

ci : re-enable type/lint-check for skills (#30713)
Sigbjørn Skjæret committed 1 month ago
3ffb629
hybrid dna tokenizer fixes (#30825)
Kashif Rasul committed 1 month ago
4c3c581
jinja : implement `unique` filter (#30819)
Aldehir Rojas committed 1 month ago
0ce8cd1
f174553
vendor : update cpp-httplib to 0.62.0 (#30785)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 1 month ago
7951f60
tests: add big-endian conversion tests (#30705)
Aaron Teo committed 1 month ago
fda00f1
CUDA: fix warning for nonexistent extra semicolon (#30774)
Johannes Gäßler committed 1 month ago
4866db3
42b7003
2b57148
tests : update Metal fusion baseline for beam (#30764)
Georgi Gerganov committed 1 month ago
27af581
pi : turn .pi/gg into a system prompt addendum (#30762)
Georgi Gerganov committed 1 month ago
7db0d3d
99db719
hexagon: allow multistream FA (#30218)
Jhen-Jie Hong committed 1 month ago
fe8841a
Restore ESIMD kernels on FFN path (#30239)
Todd Malsbary committed 1 month ago
547208d
hexagon: add support for Q1_0 and Q2_0 (#30122)
Todor Boinovski committed 1 month ago
797de63