You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
add channel wise quantization option for QDQ, and opt for intel NPU (#……669)
* add channel wise quantization option for QDQ, it optimize for intel NPU
* add channel_wised_quantize args to MatMulNBitsQuantizer
Release model proto after we have the serialized string to reduce pea…
…k memory consumption (#672)
Signed-off-by: bfilipek <bartlomiej.filipek@intel.com>
Add support for session option ep.stop_context_sharing (#655)
* Add function to query external initializer file name
* Decouple external weight processing from shared context and add support for stop context sharing