Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

ui : Discover & Download Models from HF Hub (#29584)
Aleksander Grygier committed 1 month ago
c0fd786
CUDA: faster MMVQ for low-bit types (#30517)
Aman Gupta committed 1 month ago
2744e48
9d1e036
cuda : add grouped experts top-k fusion (#29181)
Sigbjørn Skjæret committed 1 month ago
f2f667b
model : add Kolibri-1 (Aleph-Alpha) support (#30673)
Xue Zhenliang committed 1 month ago
62318cd
ci : added ABI reports as github artifact (#30619)
Sandro Hanea committed 1 month ago
83f9389
model : Granite switch decision 256 options (#30693)
Gabe Goodhart committed 1 month ago
1268eda
skills: add slice-model (#30677)
Xuan-Son Nguyen committed 1 month ago
ea0c4c2
27c7a76
model: add Beam (Reflection) (#30670)
Daniel Han committed 1 month ago
01fc3aa
model : Granite Switch Decision (#30676)
Gabe Goodhart committed 1 month ago
23f7aab
Add more benchmarks to llama-eval (#26174)
Piotr Wilkin (ilintar) committed 1 month ago
f336359
hexagon: correct HMX FA sinks (#30581)
Jhen-Jie Hong committed 1 month ago
ceefd16
model : MTP support for Mellum2.1 (#30612)
Mikhail Podvitskii committed 1 month ago
9a16f1d
3dbcb7f
c804754
sycl : reduce the build threads to half (#30236)
Neo Zhang committed 1 month ago
c0083e3