-
NVIDIA
- Champaign, IL
Block or Report
Block or report abellina
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
-
-
ucx Public
Forked from openucx/ucx
Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group):
C
-
466 contributions in the last year
Less
More
Activity overview
Contribution activity
March 2022
Created 6 commits in 2 repositories
Created a pull request in NVIDIA/spark-rapids that received 11 comments
Revert "Replace ParquetFileReader.readFooter with open() and getFooter [databricks]" [databricks]
Reverts #4976 Closes #5048. This PR #4976 looks to be causing us to read a lot more data from parquet than it used to (#5048). This reverts this, s…
+11
−18
•
11
comments
Opened 6 other pull requests in 2 repositories
NVIDIA/spark-rapids
1
open
3
merged
GoogleCloudDataproc/initialization-actions
2
merged
Reviewed 8 pull requests in 2 repositories
NVIDIA/spark-rapids
7 pull requests
- Work around incompatibility between Databricks Delta loads and GpuRegExpExtract
- Fix regression from 21.12 where udfs defined in repl no longer worked
- Fix missing imports for 321db shim [databricks]
- Add fuzzing test for JSON reader
- Update docs for the 22.04 release[skip ci]
- Fix collect_set on struct type
- Fallback to ARENA if ASYNC configured and driver < 11.5.0
rapidsai/rmm
1 pull request
Created an issue in rapidsai/cudf that received 3 comments
[BUG] JNI side is not setting the proper alignment for the limiting_resource_adaptor with ASYNC
In RmmJni, our use of limiting_resource_adaptor doesn't seem to be setting the proper alignment when wrapping the ASYNC allocator.
https://github.c…
3
comments

