Max Krasnyansky

Add support for properly optimized Windows ARM64 builds with LLVM and MSVC

12

Currently Windows ARM64 builds are not properly optimized, which results in low token rates on Windows ARM64 platforms such as the upcoming Snapgradon X-Elite & Plus. This update adds /...

Introduce Graph Profiler

6

Here is an attempt at reintroducing the original whole-graph profiler (LLAMA_PERF) with some additional features. Not ready for the merge into master but useful for profiling different models (on CPU)....