Partial Quantization Support Issue 1011 Nvidiatensorrt Github
Partial quantization support · Issue #1011 · NVIDIA/TensorRT · GitHub
Support weight only quantization from bfloat16 to int8? · Issue #110 ...
8 bit quantization calibrator error · Issue #815 · NVIDIA/TensorRT · GitHub
Support for low bit-width Quantization in TensorRT · Issue #3245 ...
Support Request: · Issue #1011 · OpenTabletDriver/OpenTabletDriver · GitHub
Does TensorRT 8.6.1 support INT8 quantization for HardSwish? - TensorRT ...
PyTorch-Quantization Toolkit · Issue #981 · NVIDIA/TensorRT · GitHub
Negative values encountered in unsigned quantization · Issue #1510 ...
Question about INT8 quantization ranges · Issue #1951 · NVIDIA/TensorRT ...
INT8 quantization with same model and different weights · Issue #2705 ...
Advertisement Space (300x250)
does NVIDIA L20 GPUs support FP8 quantization? · Issue #1914 · NVIDIA ...
Negative values encountered in unsigned quantization · Issue #1510 ...
PTQ quantization int8 is slower than fp16 · Issue #1532 · NVIDIA ...
Quantization Error Analysis on Object Detection · Issue #1114 · NVIDIA ...
Quantization Error Analysis on Object Detection · Issue #1114 · NVIDIA ...
Rules about dynamic range setting and quantization · Issue #25 · NVIDIA ...
Bug for fp8 PTQ and AWQ with AMMO quantization · Issue #216 · NVIDIA ...
Negative values encountered in unsigned quantization · Issue #1510 ...
TensorRT Explicit Quantization and Fallback to FP16 · Issue #4021 ...
Quantization flow using TensorRT (what is recommended for CNN?) · Issue ...
Advertisement Space (336x280)
Does pytorch_quantization support asymmetric-uint8 quant? · Issue #1749 ...
Quantization Error Analysis on Object Detection · Issue #1114 · NVIDIA ...
A question about int8 explicit quantization for plugins · Issue #1616 ...
AWQ quantization fails with cuda_ext import error · Issue #403 · NVIDIA ...
INT8 quantization with same model and different weights · Issue #2705 ...
Only support constant zero padding for slicing a shape tensor · Issue ...
Only support constant zero padding for slicing a shape tensor · Issue ...
int8 quantification · Issue #1023 · NVIDIA/TensorRT · GitHub
PTQ is faster than QAT · Issue #2204 · NVIDIA/TensorRT · GitHub
PyTorch-Quantization Toolkit · Issue #981 · NVIDIA/TensorRT · GitHub
Advertisement Space (336x280)
🐛 [Bug] Can't do quantization aware training for ViT · Issue #2101 ...
stable diffusion quantization in inpainting task is poor · Issue #4212 ...
TensorRT NOT match result from pytorch quantization · Issue #988 ...
Resize OP may sth wrong when use pytorch quantization · Issue #2337 ...
Quantization FP16 model using pytorch_quantization and TensorRT · Issue ...
The problem about Resnet structure in explicit quantization model ...