Actions: volcengine/verl
Actions
217 workflow runs
217 workflow runs
use_remove_padding
when applying sequence parallelism (#153)
e2e_gsm8k
#214:
Commit fb3793a
pushed
by
vermouth1992
use_remove_padding
when applying sequence parallelism
e2e_gsm8k
#211:
Pull request #153
synchronize
by
chujiezheng
_apply_liger_kernel_to_instance()
to load model
e2e_gsm8k
#198:
Pull request #133
synchronize
by
hongpeng-guo
dp_worker.py::forward_micro_batch
e2e_gsm8k
#196:
Pull request #164
opened
by
hongpeng-guo
_apply_liger_kernel_to_instance()
to load model
e2e_gsm8k
#195:
Pull request #133
synchronize
by
hongpeng-guo
use_remove_padding
when applying sequence parallelism
e2e_gsm8k
#193:
Pull request #153
synchronize
by
chujiezheng
use_remove_padding
when applying sequence parallelism
e2e_gsm8k
#189:
Pull request #153
synchronize
by
chujiezheng
use_remove_padding
when applying sequence parallelism
e2e_gsm8k
#187:
Pull request #153
opened
by
chujiezheng