feat(server): support vectorized warpers in flash causal lm #317
OlivierDehaene
marked this pull request as ready for review 2 years ago
feat(server): support vectorized warpers in flash causal lm
f9e3a3bb
fix imports
e7826855
clean dtype
b9ad3acc
add watermarking
c59fb353
optimize argmax
a62f1487
fix tests
caa96083
faster cumsum
d3cb0d3b
remove unused vars
b973c101
add shared pool
7e53903c
remove cuda graphs
e8fd0e48
OlivierDehaene
deleted the feat/vectorized_sampling branch 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub