Maxim Vafin
Maxim Vafin
### Details: - *Segfalt was accruing if protobuf structures were obtained from outside and were accessed directly* - *Refactor constant reading* - *Limit protobuf usage to `*Proto` classes* ### Tickets:...
### Context OpenVINO component responsible for support of PyTorch models is called as PyTorch Frontend (PT FE). PT FE converts a model represented as TorchScript model to a model in...
### Details: - *Support inplace `aten::sqrt_`, `aten::rsqrt_`, `aten::clamp_min_`, `aten::clamp_max_`* ### Tickets: - *ticket-id*
### Details: - *Add patch function to make 16bit models traceable. This reduce memory consumption and time spent during conversion of models that are natively saved in 16bit precision* ###...
### Details: - *Some PyTorch models may have `dicts`, `lists`, `tuples` as inputs. We unpack them on `normalize` step in PT FE, but this means that those unpacked inputs do...
### Details: - *Reformat symmetrical GPTQ to use i4 dtype* ### Tickets: - *CVS-131500*
### Details: - *Fix issue with not set decoder type rt_info* - *Remove frontend rt_info from model* ### Tickets: - *ticket-id*
### Context OpenVINO component responsible for support of PyTorch models is called as PyTorch Frontend (PT FE). PT FE converts a model represented as TorchScript model to a model in...
### Details: - *item1* - *...* ### Tickets: - *ticket-id*
### Details: - *item1* - *...* ### Tickets: - *ticket-id*