llama.cpp
c9ced491 - vulkan: preprocess mul_mat_id experts and discard workgroups more quickly (#18352)

Commit
28 days ago
vulkan: preprocess mul_mat_id experts and discard workgroups more quickly (#18352) Run a preprocess to count how many times each expert is used, and use this to quickly discard workgroups that aren't needed.
Author
Parents
Loading