text-generation-inference
feat(server): support vectorized warpers in flash causal lm
#317
Merged

feat(server): support vectorized warpers in flash causal lm #317

OlivierDehaene merged 10 commits into main from feat/vectorized_sampling
OlivierDehaene
OlivierDehaene
jlamypoirier
jlamypoirier
jlamypoirier commented on 2023-05-17
jlamypoirier
jlamypoirier commented on 2023-05-18
OlivierDehaene OlivierDehaene force pushed from 9659f82d to a021ac85 2 years ago
OlivierDehaene
OlivierDehaene OlivierDehaene marked this pull request as ready for review 2 years ago
njhill
OlivierDehaene feat(server): support vectorized warpers in flash causal lm
f9e3a3bb
OlivierDehaene fix imports
e7826855
OlivierDehaene clean dtype
b9ad3acc
OlivierDehaene add watermarking
c59fb353
OlivierDehaene optimize argmax
a62f1487
OlivierDehaene fix tests
caa96083
OlivierDehaene OlivierDehaene force pushed from bd814e6a to caa96083 2 years ago
OlivierDehaene faster cumsum
d3cb0d3b
OlivierDehaene
OlivierDehaene remove unused vars
b973c101
OlivierDehaene add shared pool
7e53903c
OlivierDehaene remove cuda graphs
e8fd0e48
OlivierDehaene OlivierDehaene merged 62f91f78 into main 2 years ago
OlivierDehaene OlivierDehaene deleted the feat/vectorized_sampling branch 2 years ago
njhill
njhill
OlivierDehaene
njhill

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone