10-12-2026, 03:12 PM
Spent some time on this today and wanted to compare notes.
I've gone back and forth between llama.cpp and vLLM for Gemma. The interesting difference for me has been speculative decoding.
Trying to avoid rebuilding the whole thing twice.
I care more about stability than squeezing the last possible tokens/sec out of it.
I've gone back and forth between llama.cpp and vLLM for Gemma. The interesting difference for me has been speculative decoding.
Trying to avoid rebuilding the whole thing twice.
I care more about stability than squeezing the last possible tokens/sec out of it.
still benchmarking everything