llama.cpp
ggml-metal: round up to 16 to fix setThreadgroupMemoryLength assertion
#3938
Merged
Merged
ggml-metal: round up to 16 to fix setThreadgroupMemoryLength assertion #3938
ggerganov
merged
1 commit into
ggml-org:master
from
psugihara:metal-multiple-of-16
ggml-metal: round up to 16 to fix MTLDebugComputeCommandEncoder asser…
8f312d91
psugihara
changed the title 
ggerganov
approved these changes
on 2023-11-03
ggerganov
commented
on 2023-11-03
Login to write a write a comment.
Login via GitHub