-
Just a quick question. I want my final model to be full int8 instead of float32 for input and outputs. I want the training to be as accurate as possible. Do I train with quantised input and outputs? B…
-
```
FAILED src/tests/test_qiskit_backend.py::TestQiskitBackend::test_coupled_qasm_hardware[hardware0] - ValueError: QiskitError while running Qiskit circuit: 'Data for experiment "circuit-313" could …
-
what to do after QAT? do i use post training quantization or i directly use the QAT model ?
thanks in advance
-
### 🐛 Describe the bug
shufflenet_v2_x1_0 QAT performance regression
model_name
qat_new
qat_old
qat ratio(new/old)
shufflenet_v2_x1_…
-
Hello,
In the qat module, I'm a little bit confusing about the way to define a quantized convolution layer with tensor quantizer. From my observation, I see that only weight quantizer is initialized …
-
### Ⅰ. Issue Description
QAT_Engine-1.5.0 ,QAT驱动:QAT.L.4.23.0-00001,OpenSSL 1.1.1w
qat fw_counter计数不增长,停留在0值。
### Ⅱ. Describe what happened
qat fw_counter计数不增长,停留在0值。
### Ⅲ. Describe what you e…
-
Are there any runnable demos of using Sparse-QAT/PTQ (2:4) to accelerate inference, such as applying PTQ to a 2:4 sparse LLaMA for inference acceleration? I am curious about the potential speedup rati…
-
I am using qat engine with proxy type TLS application and noticed that my engine references are going up with each connection. I suspected memory leak somewhere so I debugged this issue further and tu…
-
Is there a way to use qat_prf_pmeth in openssl3.0 (engine 0.6.17),
I see this in the code:
# ifndef QAT_OPENSSL_3
if (!ENGINE_set_pkey_meths(e, qat_pkey_methods)) {
WARN("ENGINE_se…
-
Prior to filing: check that this should be a bug instead of a feature request. Everything supported, including the compatible versions of TensorFlow, is listed in the overview page of each technique. …