mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-02-25 07:34:10 +00:00
0280b8d52b
This required quite a few fixes in ggml and llama.cpp: * ggml: do not calculate row size as n/block_size*type_size. I had removed most of it when implementing the quants with per row scale, bit it was stull lurking in ggml_copy. Not sure if these were the last remnants of ggmil-style row sizes, or if there are still places left * llama.cpp: get rid of the the 1d K cache assumption. Create and manage the K-cache as a 2D tensor so we can have per row meta data as needed by q8_KV. Using q8_KV for K-cache results in non-negligible performance gains. More details to follow, but for DeepSeek-Lite with MLA, we get 18% speedup for PP-8192 compared to q8_0 K-cache.