openvinotoolkit/nncf
Neural Network Compression Framework for enhanced OpenVINO™ inference
PythonApache-2.0
Issues
- 3
The question about function create_compressed_model():RuntimeError: CUDA error: device-side assert triggered
#2688 opened by zbnlala - 4
AttributeError: 'list' object has no attribute 'keys' when executing yolov8_quantize_with_accuracy_control example
#2669 opened by openvino-book - 3
- 19
- 4
- 23
- 8
- 19
[Good First Issue][NNCF]: Add INT8 weight compression conformance test for Tinyllama-1.1b PyTorch model
#2527 opened by alexsu52 - 35
[Good First Issue] [NNCF] Cover NNCF code with least coverage percentage with unit tests to at least 80%
#2496 opened by vshampor - 17
[Good First Issue] [NNCF] Make NNCF common accuracy aware training code pass mypy checks
#2492 opened by vshampor - 8
[Good First Issue][NNCF]: Optimize memory footprint by removing redundant collected statistics
#2557 opened by kshpv - 3
Concat scales not being grouped
#2195 opened by basioli-k - 1
Ultralytics yolov8 QAT example
#2489 opened by alexsu52 - 1
PTQ of Fast R-CNN crashes in PyTorch backend
#2568 opened by alexsu52 - 10
[Good First Issue][NNCF]: check number of u8, u4 constants in weight compression tests
#2565 opened by ljaljushkin - 14
- 26
- 2
Why doesn't the size and precision of the model change after INT4 quantization?
#2553 opened by xingfenghaizeiwang - 9
[Good First Issue] [NNCF] Make NNCF common tensor statistics code pass mypy checks
#2493 opened by vshampor - 5
- 6
[Good First Issue][NNCF]: Fixing NNCFGraph export for visualization in Netron
#2552 opened by andrey-churkin - 1
Thanks to our Contributors
#2499 opened by alexsu52 - 7
nncf + ultralytics yolov8 training-time compression
#2486 opened by SofyaLL - 5
[Good First Issue] [NNCF] Introduce NNCF-specific exception classes across NNCF code base for expected/avoidable error cases instead of standard `RuntimeError`
#2498 opened by vshampor - 6
- 1
SensitivityMetric is not available in nncf namespace
#2369 opened by AlexKoff88 - 0
Compressed models that call torch.is_floating_point() during inference are traced with runtime error.
#2432 opened by alexsu52 - 2
- 1
bounds incompatible with pandas 2.1.4
#2346 opened by clinty - 0
AttributeError: 'SymmetricQuantizer' object has no attribute 'register_load_state_dict_post_hook'
#2347 opened by wangqiangJN - 1
cuda
#2300 opened by YeonggulJang - 4
about saved model after quantization
#2261 opened by phhh-xh - 5
yolov8+nncf error
#2248 opened by phhh-xh - 4
- 4
Quantizing to int4 not working
#2200 opened by basioli-k - 2
AUTOload all devices failded
#2160 opened by AIgiraffe - 2
Usage examples for filter pruning
#2004 opened by cxmscb - 0
[test only] do not react please
#2215 opened by mlukasze - 16
- 5
- 1
Hessian Trace Estimate Calculation exits prematurely due to negative value of diff_avg
#2155 opened by karam-nus - 6
Error in post-training quantisation of an openvino model
#2018 opened by mnl12 - 1
- 5
Error compiling NNCF-quantized model with GRU layers
#2105 opened by akarym-sl - 4
Mobilenetv2 FP32 quant to INT8, but INT8 benchmark_app Failed Argument shapes are inconsistent.
#2103 opened by KiwiHana - 8
How to train a post-quantized onnx segmentation model?
#2022 opened by Masque555 - 4
- 2
yolov6 nncf post quantization
#2026 opened by snehashis1997 - 2
nncf 2.5 set Advanced_parameters`s weight and activation perchannel quant onnx failed
#1959 opened by AIgiraffe - 0