-
**Description**
[test_cuda_shared_memory.py
](https://github.com/triton-inference-server/client/blob/main/src/python/library/tests/test_cuda_shared_memory.py) failed when dimension of batch size is …
-
I use Linux at work but at home I have windows and would like to be able to run it on my main machine with conda. Currently when I run:
`conda env create --name pygdf_dev --file conda_environments/…
-
# Device Resident and Specific Tensors
The Tensor class in Glow is used extensively as an abstraction for typed memory on the host and is used in the compiler, runtime interfaces and backend specif…
-
### Actual behavior
```
Traceback (most recent call last):
File "demo.py", line 25, in
vm = relax.VirtualMachine(ex, tvm.cpu())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/sof…
-
In numpy.array_api, we said that type checking that inputs were `Array` was too much overhead, and we would just rely on the the type signatures and type checking to do this.
However, given that we…
-
As the MXNet community is working on the next major version of MXNet as described in #16167, this RFC seeks to clarify the scope of API deprecation, to inform the community of the replacement API desi…
-
**Describe the bug**
cuml.cluster.HDBSCAN does not appear to support precomputed distance matrix as the documentation suggests
**Steps/Code to reproduce bug**
```
from cuml.cluster import HDBSCA…
-
**Describe the bug**
When trying to build onnxruntime with the Vitis-AI runtime according to the build instructions at https://onnxruntime.ai/docs/reference/execution-providers/Vitis-AI-ExecutionProv…
-
**Is your feature request related to a problem? Please describe.**
I know we can copy GPU tensor to CPU with `torch.utils.dlpack.from_dlpack` ([link](https://github.com/triton-inference-server/server…
-
cd /dev/shm/multitask/mx-maskrcnn/incubator-mxnet/dmlc-core; make libdmlc.a USE_SSE=1 config=/dev/shm/multitask/mx-maskrcnn/incubator-mxnet/make/config.mk; cd /dev/shm/multitask/mx-maskrcnn/incubator-…