speculative : PoC for speeding-up inference via speculative sampling #2926
ggerganov
force pushed
from
22f7a9dd
to
fdc53e2c
2 years ago
ggerganov
changed the base branch from
master
to
build-metal-default
2 years ago
ggerganov
changed the base branch from
build-metal-default
to
master
2 years ago
ggerganov
force pushed
from
fdc53e2c
to
c33cd8ad
2 years ago
speculative : initial example
c82c808d
speculative : print encoding speed
a15ca746
ggerganov
force pushed
from
5c2aad7f
to
a15ca746
2 years ago
speculative : add --draft CLI arg
847896ab
ggerganov
merged
47068e51
into master 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub