aws-neuron
/

optimum-neuron-cache

Model card Files Files and versions Community

optimum-neuron-cache / neuronxcc-2.15.128.0+56dc5a86 /MODULE_0bf6d289104e18c64e40+39f12043 /compile_flags.json

dacorvo's picture

dacorvo HF staff

Synchronizing local compiler cache.

ed72e17 verified 2 months ago

74 Bytes

["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]