-
Notifications
You must be signed in to change notification settings - Fork 377
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Support native torch embedded quantization encodings #2305
Support native torch embedded quantization encodings #2305
Commits on Jun 30, 2023
-
Support for native Pytorch embedded quantization encodings (quic#1156)
Signed-off-by: Huan Zhao <quic_huzh@quicinc.com> Support FP16 native torch quantizer using cast Signed-off-by: Huan Zhao <quic_huzh@quicinc.com> Fixed some comment Signed-off-by: Huan Zhao <quic_huzh@quicinc.com> Move functions related to quantizer to quantsim_utils Signed-off-by: Huan Zhao <quic_huzh@quicinc.com> Removed uncertain check caused by different version of onnx Signed-off-by: Huan Zhao <quic_huzh@quicinc.com> Change API to call embedded encodings from single function to sim.export Signed-off-by: Huan Zhao <quic_huzh@quicinc.com> Renamed use_embedded_encodings and raise error when use strict symmetric. Signed-off-by: Huan Zhao <quic_huzh@quicinc.com> Resolved conflicts and added testing cases to ensure the output of native torch quantization nodes is correct Signed-off-by: Huan Zhao <quic_huzh@quicinc.com>
Configuration menu - View commit details
-
Copy full SHA for 4d91499 - Browse repository at this point
Copy the full SHA 4d91499View commit details -
Add test cases for LearnedGridQuantizer and use OnnxSaver._export_mod…
…el_to_onnx Signed-off-by: Huan Zhao <quic_huzh@quicinc.com>
Configuration menu - View commit details
-
Copy full SHA for ca2639c - Browse repository at this point
Copy the full SHA ca2639cView commit details -
Signed-off-by: Huan Zhao <quic_huzh@quicinc.com>
Configuration menu - View commit details
-
Copy full SHA for 8dbf173 - Browse repository at this point
Copy the full SHA 8dbf173View commit details -
Fixed QcQuantizeOpMode while using LearnedGrid Quantizer
Signed-off-by: Huan Zhao <quic_huzh@quicinc.com>
Configuration menu - View commit details
-
Copy full SHA for a20f125 - Browse repository at this point
Copy the full SHA a20f125View commit details -
Remove default parameters of save_model_with_embedded_quantization_nodes
Signed-off-by: Huan Zhao <quic_huzh@quicinc.com>
Configuration menu - View commit details
-
Copy full SHA for 7072cb5 - Browse repository at this point
Copy the full SHA 7072cb5View commit details -
Add check to avoid non 8 bit torch quantizers are exported to ONNX
Signed-off-by: Huan Zhao <quic_huzh@quicinc.com>
Configuration menu - View commit details
-
Copy full SHA for 2cc278a - Browse repository at this point
Copy the full SHA 2cc278aView commit details -
Removed _mode and add checker for bias
Signed-off-by: Huan Zhao <quic_huzh@quicinc.com>
Configuration menu - View commit details
-
Copy full SHA for 5f83fab - Browse repository at this point
Copy the full SHA 5f83fabView commit details -
Fix exported bug caused by device
Signed-off-by: Huan Zhao <quic_huzh@quicinc.com>
Configuration menu - View commit details
-
Copy full SHA for a38be5d - Browse repository at this point
Copy the full SHA a38be5dView commit details -
Change code to torch_quantizer.py and remove redundant per_channel flag
Signed-off-by: Huan Zhao <quic_huzh@quicinc.com>
Configuration menu - View commit details
-
Copy full SHA for 737cff5 - Browse repository at this point
Copy the full SHA 737cff5View commit details