Fix GQA permutation computation and sequential weight initialization / loading when doing TP #808
test_trainium_common.yml
on: pull_request
optimum-neuron-tests
0s
Annotations
1 error
optimum-neuron-tests
Canceling since a higher priority waiting request for 'Optimum Neuron - Common tests on Trainium-fix_gqa_compute_query_indicies' exists
|