Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

model : extend Nemotron MTP support (#29018)
Kartik Gulia committed 2 months ago
7076180
ebbb185
87f9c82
c9a5eee
opencl: fix various warnings (#28984)
lhez committed 2 months ago
c57da6f
docs: remove JG as CODEOWNER for test-llama-archs (#29003)
Johannes Gäßler committed 2 months ago
79bfc1d
vulkan: support qwen4exp hc ops (#28988)
Ruben Ortlam committed 2 months ago
35822af
4bc272f
c6824a9
Enable CUDA graph for MTP draft (#28549)
Gaurav Garg committed 2 months ago
2f3fd02
hexagon: Support for K-Quants Q4_K and Q6_K (#28994)
Marco Colombo committed 2 months ago
1ec8188
82324fc
qwen4exp: add hc ops (#28901)
Aman Gupta committed 2 months ago
37b53fd