Mingyu Kim

Results 6 issues of Mingyu Kim

category: inference
category: GPU
category: C API
category: docs
category: CPP API

### Details: - *item1* - *...* ### Tickets: - *ticket-id*

category: GPU
category: build
do_not_merge

### Details: - Integrate OneDNN dynamic quantization - OneDNN change is not upstreamed yet. ### Tickets: - 144522

category: GPU
do_not_merge

### Details: - New debug config for dumping verbose log into file

category: GPU

### Details: - It is applied only to int4 compressed model, non-systolic path - Though it is a global configuration, systolic hardware will ignore it ### Tickets: - 151708

category: GPU
priority: high
Code Freeze

### Details: - Make OCL context as singleton - GenAI tries to change its behavior to multi ov::Core, while buffers can be shared across ov::Core - We had two choices...

category: inference
category: GPU
category: Python API
category: docs
category: CPP API
category: JS API