-
### Description
I recently had a user notice a slowdown while summing a sparse CSR matrix along the major axis. After some tinkering, I created a new method for summing across the major axis that w…
-
### 🐛 Describe the bug
Hey,
First of all, thanks for creating such a fantastic open-source production server.
I'm reaching out due an unexpected issue I can't solve. I've been running a torch…
-
When spark-rapids-jni finished building, it prints out a log message like this:
```
[INFO] ------------------------------------------------------------------------
[INFO] BUILD SUCCESS
[INFO] ----…
-
Hi,
I am trying the hlca_lung_gpu notebook with my own data to test the dimensionality reduction on GPU. The notebook is running well (data loading, pca...) until the nearest neighbors computation
…
-
Seems to be a Rapids issue
gets error:
06-01 13:39:04.946 172.16.2.46:54321 79560 # Session INFO: Method: POST , URI: /3/Rapids, route: /3/Rapids, parms: {ast=(= !nary_op_2 (apply %r.hex #2 …
-
## Description
RAPIDS supports CUDA 11.x and 12.x, and has for a couple of releases.
Throughout the examples in this repo, most examples default to CUDA 11. For example:
https://github.com/ra…
-
The README file points to an older version of spark-rapids. See link to downloading jar [spark-rapids jar](https://github.com/NVIDIA/spark-rapids-benchmarks/tree/dev/nds#convert-csv-to-parquet-or-othe…
-
**Is your feature request related to a problem? Please describe.**
I'm using RAFT by rapids.cmake, while errors occur sometime related to cmake, it's hard to debug, usually I need to remove all build…
-
**Describe the bug**
Connecting `Client(synchronous=False)` to a `LocalCUDACluster(synchronous=True)` hangs. This means an async localcudacluster cannot be used with RAPIDS libraries that expect a…
-
Currently, we use a patch to remove `nvidia-nccl-cu12` from the dependencies when building the CPU wheel:
https://github.com/dmlc/xgboost/blob/f52f11e1d7c3e2c5b065f8fca6defc818089cebc/tests/buildkite…
hcho3 updated
2 months ago