-
**Describe the bug**
I tried to optimize BERT model with bert_ptq_cpu.json but it gave 7 output models.
It there any ways or change the config to get only one output model?
```
[2024-10-25 10:54:59,1…
-
Converting this dummy model with quantize_target_type="int8" and per_tensor=True throws an error in tflite
```python
import torch.nn as nn
import torch
from tinynn.graph.quantization.quantizer …
-
### 🚀 The feature, motivation and pitch
I am trying to implement eager mode of PT2E quantization on CPU. Currently, the PT2E quantization on CPU is lowered to Inductor by `torch.compile`. The current…
-
We've been struggling too much with setting up running 6 models from Whisperer Challenge. Over the weekend, I researched some existing HSI dataset, probably with HSI dataset. Here's some [chat log](ht…
-
I'm currently using H800 to do Smooth Quantization for my custom flux transformer. I'm wondering how long it would take to finish quantization. I have been quantizing for 20 minutes, but the progress …
-
alerte google sur la non indexation de stop-punaises
depuis la bascule vers gouv.fr on a n a pas fait la modif
il faudrait enregistrer
google-site-verification=oo3X0P7UHeG-eZHsKNUDrcmUX8Ywch13TcaTLsG…
-
. Quantizes its argument in the forward pas…
-
Hi, guys, Im wondering would smoothquant be supported in the future for int8 *onnx* quant?
Mainly for VIT-like model and LLM.