Skip to content

gguf: optimize prefill speeds for Q4_K quants#1395

Open
AlpinDale wants to merge 3 commits into
mainfrom
q4k_prefill_optim
Open

gguf: optimize prefill speeds for Q4_K quants#1395
AlpinDale wants to merge 3 commits into
mainfrom
q4k_prefill_optim

better shared memory calculation for q4k

bde0968
Select commit
Loading
Failed to load commit list.