NVIDIA/cudf-spark-tools

Issues somebody may already be working on are listed last. List everything by date

• [BUG] On Databricks logs, AutoTuner compares the runtime string (e.g. 17.3.x-photon-scala2.13) as if it were the Apache Spark version

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage bug

  Difficulty 4/5 1-2 days Newbie friendliness 30/100

  NVIDIA/cudf-spark-tools#2192 · Opened Oct 15, 2026

  Maintainers usually reply within 1 day

• [BUG] Qualification scores Delta MERGE, UPDATE and DELETE on Databricks as supported, but the plugin runs them on CPU by default

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage bug

  Difficulty 4/5 3-5 days Newbie friendliness 18/100

  NVIDIA/cudf-spark-tools#2191 · Opened Oct 15, 2026

  Maintainers usually reply within 1 day

• [DOC] Databricks-Azure guide: removed commands, invalid ABFS URL examples, and missing ABFS access/auth details

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage documentation user_tools

  Difficulty 2/5 Half a day Newbie friendliness 62/100

  NVIDIA/cudf-spark-tools#2190 · Opened Oct 14, 2026

  Maintainers usually reply within 1 day

• [BUG] stages.csv counts a Delta MERGE's child stages twice, and a stage's unsupported time can exceed its task time

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage bug

  Difficulty 4/5 3-5 days Newbie friendliness 28/100

  NVIDIA/cudf-spark-tools#2189 · Opened Oct 14, 2026

  Maintainers usually reply within 1 day

• [FEA] Update the QualX Photon models for Databricks 17.3

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  feature request qualx

  Difficulty 5/5 Over a week Newbie friendliness 12/100

  NVIDIA/cudf-spark-tools#2187 · Opened Oct 14, 2026

  Maintainers usually reply within 1 day

• [FEA] Add a successful-attempt output records metric

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage feature request

  Difficulty 4/5 3-5 days Newbie friendliness 32/100

  NVIDIA/cudf-spark-tools#2185 · Opened Oct 8, 2026

  Maintainers usually reply within 1 day

• [FEA] Validate Databricks 17.3 Photon SQL metric labels and units

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 4/5 3-5 days Newbie friendliness 48/100

  NVIDIA/cudf-spark-tools#2175 · Opened Sep 29, 2026

  Maintainers usually reply within 1 day

• [FEA] AutoTuner: say whether an application is a good fit for multithreaded shuffle skipMerge

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage autotuner feature request

  Difficulty 4/5 3-5 days Newbie friendliness 45/100

  NVIDIA/cudf-spark-tools#2174 · Opened Sep 23, 2026

  Maintainers usually reply within 1 day

• [FEA] Support dual cudf-spark jar patterns

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage audit_plugin feature request

  Difficulty 2/5 1-3 hours Newbie friendliness 68/100

  NVIDIA/cudf-spark-tools#2169 · Opened Sep 18, 2026

  Maintainers usually reply within 1 day

• [FEA] Sync aliasing configurations with spark-cudf plugin

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage audit_plugin feature request

  Difficulty 3/5 1-2 days Newbie friendliness 58/100

  NVIDIA/cudf-spark-tools#2167 · Opened Sep 16, 2026

  Maintainers usually reply within 1 day

• [BUG] AutoTuner aborts while parsing malformed typed source properties

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage autotuner bug

  Difficulty 5/5 Over a week Newbie friendliness 45/100

  NVIDIA/cudf-spark-tools#2166 · Opened Sep 16, 2026

  Maintainers usually reply within 1 day

• [FEA] Let heuristics declare their own version requirements instead of inline comparisons

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage autotuner feature request

  Difficulty 5/5 Over a week Newbie friendliness 35/100

  NVIDIA/cudf-spark-tools#2157 · Opened Sep 10, 2026

  Maintainers usually reply within 1 day

• [BUG] QualX supported-stage filter is computed but not applied to feature aggregation

  May be free again @hirakendu claimed this 36 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage bug qualx

  NVIDIA/cudf-spark-tools#2156 · 1 assignee · Opened Sep 10, 2026

  Maintainers usually reply within 1 day

• [BUG] median columns publish a truncating rolling mean, not a median

  May be free again @amahussein claimed this 42 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage api_change bug core_tools

  NVIDIA/cudf-spark-tools#2140 · 1 comment · 1 assignee · Opened Sep 4, 2026

  Maintainers usually reply within 1 day

• Follow-ups from the downward shuffle partition pass (#2129)

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 5/5 Over a week Newbie friendliness 35/100

  NVIDIA/cudf-spark-tools#2133 · Opened Sep 1, 2026

  Maintainers usually reply within 1 day

• [FEA] Give the AutoTuner a signal for GPU memory skew within a stage

  May be free again @amahussein claimed this 45 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  autotuner feature request

  NVIDIA/cudf-spark-tools#2132 · 1 assignee · Opened Sep 1, 2026

  Maintainers usually reply within 1 day

• [FEA] Recognize noop V2 DataFrame writes and emit correct write-operation metadata

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 4/5 3-5 days Newbie friendliness 65/100

  NVIDIA/cudf-spark-tools#2126 · Opened Aug 20, 2026

  Maintainers usually reply within 1 day

• [BUG] Status CSV reports success when AutoTuner fails

  May be free again @parthosa claimed this 81 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  autotuner bug

  NVIDIA/cudf-spark-tools#2113 · 1 assignee · Opened Jul 27, 2026

  Maintainers usually reply within 1 day

• Auto-tuner: Recommend PerfIO CRT HTTP client and S3 concurrency for EMR + Iceberg workloads

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  autotuner

  Difficulty 4/5 3-5 days Newbie friendliness 64/100

  NVIDIA/cudf-spark-tools#2111 · 1 comment · Opened Jul 21, 2026

  Maintainers usually reply within 1 day

• [FEA] AutoTuner: Recommend Iceberg catalog cache TTL config for Iceberg jobs

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage autotuner feature request

  Difficulty 4/5 3-5 days Newbie friendliness 65/100

  NVIDIA/cudf-spark-tools#2110 · 1 reaction · Opened Jul 7, 2026

  Maintainers usually reply within 1 day

• [FEA] Add a special report for PerfIO

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage feature request

  Difficulty 5/5 Over a week Newbie friendliness 35/100

  NVIDIA/cudf-spark-tools#2103 · Opened Jun 15, 2026

  Maintainers usually reply within 1 day

• [FEA] Profiling tool supports honoring the Dataproc Serverless 3.0's requirements

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage feature request

  Difficulty 5/5 Over a week Newbie friendliness 45/100

  NVIDIA/cudf-spark-tools#2091 · Opened May 2, 2026

  Maintainers usually reply within 1 day

• Support AWS profile endpoint_url for S3-compatible object stores

  May be free again A pull request for this issue was closed without being merged. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel

  Difficulty 4/5 3-5 days Newbie friendliness 58/100

  NVIDIA/cudf-spark-tools#2087 · Opened Apr 24, 2026

  Maintainers usually reply within 1 day

• Add live Spark Connect event-log integration test coverage

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  feature request

  Difficulty 4/5 3-5 days Newbie friendliness 48/100

  NVIDIA/cudf-spark-tools#2085 · Opened Apr 22, 2026

  Maintainers usually reply within 1 day

• Refactor user_tools API tests to add shared profiler fixture base

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  feature request

  Difficulty 3/5 1-2 days Newbie friendliness 65/100

  NVIDIA/cudf-spark-tools#2084 · Opened Apr 22, 2026

  Maintainers usually reply within 1 day

• [FEA] Tools should output some information related to whether a spark job succeeds or not

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage feature request

  Difficulty 5/5 Over a week Newbie friendliness 35/100

  NVIDIA/cudf-spark-tools#2083 · 1 comment · Opened Apr 22, 2026

  Maintainers usually reply within 1 day

• [BUG] AutoTuner should consider actual heap usage from event log when reducing heap

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage autotuner bug

  Difficulty 4/5 3-5 days Newbie friendliness 48/100

  NVIDIA/cudf-spark-tools#2077 · Opened Apr 17, 2026

  Maintainers usually reply within 1 day

• [BUG] Python UDF exec deduplication for duration estimates

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage bug

  Difficulty 3/5 1-2 days Newbie friendliness 68/100

  NVIDIA/cudf-spark-tools#2068 · Opened Apr 2, 2026

  Maintainers usually reply within 1 day

• [FEA] Spark Connect eventlog support for tools

  May be free again @sayedbilalbari claimed this 205 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  feature request

  NVIDIA/cudf-spark-tools#2058 · 1 comment · 1 assignee · Opened Mar 25, 2026

  Maintainers usually reply within 1 day

• [BUG] Back port Subquery UI change from Spark4.2

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage bug core_tools

  Difficulty 4/5 3-5 days Newbie friendliness 45/100

  NVIDIA/cudf-spark-tools#2057 · Opened Mar 18, 2026

  Maintainers usually reply within 1 day

• [BUG] KeyError: 'appId' in QualX feature extraction for certain GPU eventlogs

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage bug qualx

  Difficulty 3/5 1-2 days Newbie friendliness 48/100

  NVIDIA/cudf-spark-tools#2050 · Opened Mar 5, 2026

  Maintainers usually reply within 1 day

• [BUG] RAPIDS_USER_TOOLS_GPU_SPEEDUP_SPARK_LOWER_BOUND - does not update the Categorization

  May be free again @sayedbilalbari claimed this 232 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  bug

  NVIDIA/cudf-spark-tools#2044 · 1 assignee · Opened Feb 26, 2026

  Maintainers usually reply within 1 day

• [BUG] support new EMR instance types

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage bug

  Difficulty 3/5 1-2 days Newbie friendliness 42/100

  NVIDIA/cudf-spark-tools#2043 · 4 comments · Opened Feb 25, 2026

  Maintainers usually reply within 1 day

• [FEA] Comet support for Qual tool

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage feature request

  Difficulty 5/5 Over a week Newbie friendliness 25/100

  NVIDIA/cudf-spark-tools#2038 · Opened Feb 19, 2026

  Maintainers usually reply within 1 day

• [BUG] Recommended cluster shape is based on spark.executor.instances rather than actual executors used

  May be free again @SYangster claimed this 262 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage autotuner bug

  NVIDIA/cudf-spark-tools#2033 · 1 assignee · Opened Jan 28, 2026

  Maintainers usually reply within 1 day

• [BUG] OutputAdapter is marked as unsupported in Qual tool

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage bug

  Difficulty 3/5 1-2 days Newbie friendliness 45/100

  NVIDIA/cudf-spark-tools#2032 · Opened Jan 27, 2026

  Maintainers usually reply within 1 day

• [FEA] Add job properties in profiling tool results

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  ? - Needs Triage core_tools feature request

  Difficulty 3/5 1-2 days Newbie friendliness 45/100

  NVIDIA/cudf-spark-tools#2030 · 1 comment · Opened Jan 26, 2026

  Maintainers usually reply within 1 day

• [FEA] Improve analysis of GPU eventlogs based on GPU metrics

  May be free again @parthosa claimed this 199 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  core_tools feature request

  NVIDIA/cudf-spark-tools#2020 · 1 comment · 1 reaction · 1 assignee · Opened Jan 6, 2026

  Maintainers usually reply within 1 day

• Consolidate Platform Configurations to YAML

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  core_tools

  Difficulty 5/5 Over a week Newbie friendliness 35/100

  NVIDIA/cudf-spark-tools#2019 · Opened Jan 5, 2026

  Maintainers usually reply within 1 day

• Remove Unused Cluster Creation Script Generation Feature

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  user_tools

  Difficulty 4/5 3-5 days Newbie friendliness 42/100

  NVIDIA/cudf-spark-tools#2018 · Opened Jan 5, 2026

  Maintainers usually reply within 1 day

• [FEA] Sync supported ops with RAPIDS plugin 25.12

  May be free again @sayedbilalbari claimed this 289 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  audit_plugin core_tools

  NVIDIA/cudf-spark-tools#2006 · 1 assignee · Opened Dec 23, 2025

  Maintainers usually reply within 1 day

• [BUG] In QUALX, the value of sql_ops_xxx is binary.

  May be free again @hirakendu claimed this 277 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  question

  NVIDIA/cudf-spark-tools#2002 · 3 comments · 1 assignee · Opened Dec 17, 2025

  Maintainers usually reply within 1 day

• [QST] The model performed poorly when I used my own data.

  May be free again @hirakendu claimed this 261 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  question

  NVIDIA/cudf-spark-tools#1995 · 4 comments · 1 assignee · Opened Dec 15, 2025

  Maintainers usually reply within 1 day

• [FEA] Support eventlogs produced by Gluten

  May be free again @sayedbilalbari claimed this 283 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  core_tools feature request

  NVIDIA/cudf-spark-tools#1991 · 1 assignee · Opened Dec 4, 2025

  Maintainers usually reply within 1 day

• [FEA] Artifact download messaging not very understandable

  May be free again @sayedbilalbari claimed this 319 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  feature request

  NVIDIA/cudf-spark-tools#1983 · 1 assignee · Opened Dec 1, 2025

  Maintainers usually reply within 1 day

• [FEA] Support eventlogs produced by different native query execution engines

  May be free again @amahussein claimed this 337 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  core_tools feature request

  NVIDIA/cudf-spark-tools#1978 · 2 comments · 1 assignee · Opened Nov 6, 2025

  Maintainers usually reply within 1 day

• [DOC] It would be nice to have a guide doc for auto-tuner feature

  May be free again @parthosa claimed this 345 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  documentation

  NVIDIA/cudf-spark-tools#1969 · 2 comments · 1 assignee · Opened Oct 24, 2025

  Maintainers usually reply within 1 day

• [FEA] Auto-Tuner testing framework

  May be free again @sayedbilalbari claimed this 345 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  autotuner test

  NVIDIA/cudf-spark-tools#1964 · 1 assignee · Opened Oct 17, 2025

  Maintainers usually reply within 1 day

• [BUG] Update `aws-java-sdk` dependencies to V2 for >= hadoop 3.4.x

  Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  bug

  Difficulty 3/5 1-2 days Newbie friendliness 42/100

  NVIDIA/cudf-spark-tools#1962 · 2 comments · Opened Oct 3, 2025

  Maintainers usually reply within 1 day

• Autotuner: Add GPU recommendations for Delta Lake

  May be free again @amahussein claimed this 346 days ago, and no pull request is open. Open

  ⋯Report a problem with this issue

  • Is something wrong?

  • Already taken
  • Not beginner-friendly
  • Stale or invalid
  • Something else…
  • Send Cancel
  autotuner

  NVIDIA/cudf-spark-tools#1961 · 1 comment · 1 assignee · Opened Oct 3, 2025

  Maintainers usually reply within 1 day