LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Ecosystems
Launchpads

Search

Other

ggml

Tensor library for machine learning

OtherEmerging

Stars

5

Forks

—

Contributors

8

Last push

9d ago

Recent commits

Latest commits.

ggml : bump version to 0.13.1 (#1523)
1e33fedGeorgi Gerganov19d ago
sync : llama.cpp
5fbba2fGeorgi Gerganov19d ago
cuda : disables launch_fattn PDL enrollment due to compiler bug (llama/23825)
3076f42Andreas Kieslinger19d ago
meta : Add missing `buffer` set in allreduce fallback !COMPUTE clear (llama/23480)
a877961Matt Corallo19d ago
hexagon: basic/generic op fusion support and RMS_NORM+MUL fusion (llama/23835)
f42b7c3Max Krasnyansky19d ago

opencl: move backend info printing into its own function (llama/23702)

977143dlhez19d ago

ggml: auto apply iGPU flag CUDA/HIP if integrated device (llama/23007)

b93a3cdfl0rianr19d ago

mmvq Optim: add MMVQ_PARAMETERS_TURING(mmvq_parameter_table_id) for … (#23729)

a2c8f04redfox19d ago

Top contributors

Builders behind this project.

JohannesGaessler