Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

gguf : reject empty metadata keys (#24917)
Rohit Mahesh committed 4 months ago
d72bfa3
server: allow stream for exec_shell_command (#25526)
Xuan-Son Nguyen committed 4 months ago
c92e806
server: refactor server_stream (#25541)
Xuan-Son Nguyen committed 4 months ago
ea1f7bb
76f2798
server: accept null sampling params (#25538)
Pascal committed 4 months ago
4f37f51
c749cb0
67776ea
arg: prevent duplicate spec model downloads (#25527)
Xuan-Son Nguyen committed 4 months ago
22b69b6
mtmd: deepseek-ocr v1 multi-tile (#24717)
Xuan-Son Nguyen committed 4 months ago
3e706dd
ui: use server modalities in non-router mode (#24874)
Josh Leverette committed 4 months ago
9f623c6
server: remove loading.html (#25500)
Xuan-Son Nguyen committed 4 months ago
a935fbf
sync : ggml
Georgi Gerganov committed 4 months ago
0badc06
ggml : use ggml_vqtbl1q_u8 for 32-bit compat (whisper/0)
Georgi Gerganov committed 4 months ago
ac17f8a
server: improve tools, remove apply_diff (#25498)
Xuan-Son Nguyen committed 4 months ago
c4ae9a8
cli: fix crash on wrong server base url (#25497)
marcoStocchi committed 4 months ago
1b9691b
sync : ggml (#25517)
Georgi Gerganov committed 4 months ago
8f114a9
ggml-et: Initial ET backend (#24179)
Martin Chang committed 4 months ago
082b326
llama-batch: add unit test (#25471)
Aman Gupta committed 4 months ago
961e4b2
opencl: cluster-parallel decode FA for Adreno (#25473)
Hongqiang Wang committed 4 months ago
049326a
cli: add --output option (#25484)
Xuan-Son Nguyen committed 4 months ago
3de7dd4