llama.cpp
bba84088 - Add LLAMA_MOE_RANDOM_ROUTING=1 for benchmark-only random expert selection (#29539)

Commit
1 day ago
Add LLAMA_MOE_RANDOM_ROUTING=1 for benchmark-only random expert selection (#29539) * Add LLAMA_MOE_RANDOM_ROUTING=1 for benchmark-only random expert selection * Handle expert caching
Author
Parents
Loading