Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

b933289
c328acc
qwen4exp : optimize mask constructions (#29824)
Georgi Gerganov committed 1 month ago
4e2713c
631109b
ci : fix missing zdnn backend check (#29837)
Aaron Teo committed 1 month ago
254b177
fb4b273
207bdab
hexagon: install rebuilt HTP skels (#29828)
kurquhar committed 1 month ago
5fc4f3c
qwen4exp: fix tests (#29819)
Aman Gupta committed 1 month ago
159c651
hexagon: add q2_k and q3_k quant type support (#29717)
Jhen-Jie Hong committed 1 month ago
a868c3e
CUDA: fix 2 broken Volta FA cases (#29803)
Johannes Gäßler committed 1 month ago
ec7630a
llama: refer to segment documentation [no ci] (#29074)
Johannes Gäßler committed 1 month ago
78e2964
68e79bd
81e39ad
metal : release temporary private transfer buffers (#29777)
Mike van Lammeren committed 1 month ago
13b4d71
llama : fix invalid assert in recurrent memory (#29799)
Georgi Gerganov committed 1 month ago
869034b
Qwen4Exp: add MTP (#29761)
Aman Gupta committed 1 month ago
c061df1
llama: fix qwen4exp (#29751)
Aman Gupta committed 1 month ago
66e0c17
552f18f