backend : add eval callback #4935
backend : add eval callback
65648b34
backend : group nodes in a single compute when user don't need them
01b6f68a
backend : clean-up the implementation
83f3d7a8
ggerganov
force pushed
to
83f3d7a8
2 years ago
ggerganov
marked this pull request as ready for review 2 years ago
simple : do not perform tensor data copy if not needed
e1b1db9f
simple : fix
e0493800
slaren
commented
on 2024-01-15
slaren
commented
on 2024-01-15
slaren
commented
on 2024-01-15
slaren
commented
on 2024-01-15
simple : no need for ggml_is_contiguous + fix bool parse
aa16b544
llama : fix callback placement in llama_context_params
0c96c721
backend : avoid double-ask callback calls
012ecec5
slaren
commented
on 2024-01-16
slaren
approved these changes
on 2024-01-16
simple : restore examples, imatrix will serve as a demo
200dcaf7
ggerganov
merged
44a1a4a4
into master 2 years ago
ggerganov
deleted the gg/sched-eval-callback-4931 branch 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub