-
**Describe the bug**
Running a forward pass on a `DeepSpeedTransformerInference` layer, with a sequence length of ~1000 tokens, results in an illegal memory access CUDA error.
**To Reproduce**
He…
-
**Describe the bug**
Fused GEMM example gives the wrong result for some values of `problemSize1.K`.
**Steps/Code to reproduce bug**
Set the following problem sizes in `examples/13_two_tensor_op_f…
-
Hello,
I have trained an `OPQ128_512,IVF262144_HNSW32,PQ128x6`, and it took some time! Would it be possible to avoid training again, but to just transfer the IVF index to another index, but with a …
-
In the path of `arch/pretrained_model`, i use under shell to convert model to tflite.
```shell
tflite_convert ^
--output_file MobileFaceNet_9925_9680.tflite ^
--graph_def_file MobileFaceNet_99…
-
Hi,
I am trying to do,
`
n2d2 resnet-18-v1-onnx.ini -seed 1 -w /dev/null -export CPP -nbbits -32`
but after compiling the network Accuracy is 0%
but if I test the onnx directly I get 70%
…
-
# Summary
I have updated the overview figure because AQ and 4-bit PQ have been implemented. Let me know if there're papers that should appear in this figure :)
. If your issue is more general, please create your issue h…