Skip to content

Pull requests: NVIDIA-NeMo/Skills

New pull request New
43 Open 1,159 Closed
43 Open 1,159 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

update vllm dockerfile for ray
#1392 opened Apr 21, 2026 by wedu-nvidia Collaborator Loading…
9
update slurm test for nano v3
#1389 opened Apr 21, 2026 by wedu-nvidia Collaborator • Draft
5
Add Wikipedia search MCP tool with tests and dependency
#1388 opened Apr 21, 2026 by tamohannes Collaborator Loading…
3 tasks done
10
Add ArXiv search MCP tool with tests and dependency
#1387 opened Apr 21, 2026 by tamohannes Collaborator Loading…
3 tasks done
6
Add FLEURS multilingual ASR/AST benchmark with multilingual normalization
#1384 opened Apr 19, 2026 by naymaraq Collaborator Loading…
19
Expose frequency and presence penalty in inference configs for use with ns eval
#1383 opened Apr 17, 2026 by shuoyangd Collaborator • Draft
3
Use upstream NeMo-RL entrypoints and simplify sandbox integration
#1381 opened Apr 17, 2026 by wedu-nvidia Collaborator Loading…
23
Multimodel profiling instead of difficulty estimation
#1380 opened Apr 17, 2026 by tatevik-t Collaborator • Draft
Add MT-Bench and Komt-Bench (Korean MT-Bench) benchmarks
#1378 opened Apr 17, 2026 by bzantium Contributor Loading…
3 tasks
1
13
Add universal lock files for sandbox run GPU tests
#1376 opened Apr 17, 2026 by activatedgeek Collaborator Loading…
2
Add Korean benchmarks: KMMLU, KMMLU-Pro, KMMLU-Redux, KoIFEval, KorMedMCQA, KoSimpleQA
#1375 opened Apr 17, 2026 by bzantium Contributor Loading…
4 tasks
1
14
fix: align HLE answer extraction with prompt format
#1373 opened Apr 16, 2026 by tamohannes Collaborator Loading…
3
Integrating SWE-Atlas-QnA benchmark evaluation
#1366 opened Apr 15, 2026 by wasiahmad Collaborator • Draft
4
Add ContextASR-Bench benchmark (contextual ASR with NE-WER/NE-FNR metrics)
#1365 opened Apr 15, 2026 by KunalDhawan Loading…
5 tasks
21
Add document-level translation benchmarks
#1358 opened Apr 13, 2026 by jeffwillette Collaborator Loading…
50
Support SAFIM benchmark evaluation
#1355 opened Apr 8, 2026 by wasiahmad Collaborator • Draft
15
[Low priority feat] Add rerun rate-limit error resume support
#1351 opened Apr 8, 2026 by sgunasekar Collaborator • Draft
4
[Feat] Add sandbox_mounts cluster config field with r/w permission support reviewed run GPU tests
#1350 opened Apr 8, 2026 by sgunasekar Collaborator Loading…
14
style controlled arena-hard
#1346 opened Apr 7, 2026 by jveronvialard Collaborator Loading…
22
SALM Backend Support and HF ASR Leaderboard Evaluation Recipe run GPU tests
#1344 opened Apr 6, 2026 by melllinia Member Loading…
29
Add few-shot support for MMLU-ProX
#1336 opened Apr 2, 2026 by shuoyangd Collaborator Loading…
11
Add vLLM ASR backend for multimodal speech recognition
#1308 opened Mar 15, 2026 by DongjiGao Contributor Loading…
4 tasks done
22
Rectified logic for system prompt and audio trimming.
#1298 opened Mar 10, 2026 by ankitapasad • Draft
2
eval kit support v2 run GPU tests
#1295 opened Mar 7, 2026 by Jorjeous Member Loading…
20
Update with different dataset source run GPU tests
#1291 opened Mar 4, 2026 by Jorjeous Member Loading…
1
ProTip! Exclude everything labeled bug with -label:bug.