Skip to content

Pull requests: mlcommons/inference

New pull request New
49 Open 1,585 Closed
49 Open 1,585 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

fix(e2e-rag): drop the duplicated second half of QSL.py
#2673 opened Sep 11, 2026 by Anai-Guo Loading…
1
Default --audit-conf to audit.config in the reference entry points
#2672 opened Sep 11, 2026 by 100-JM Loading…
1
llama3.1-8b: fix run scripts and the README accuracy flow
#2671 opened Sep 11, 2026 by 100-JM Loading…
2
llama3.1-8b: use TokensPrompt in the Offline vLLM SUT and fail fast on worker death
#2670 opened Sep 11, 2026 by 100-JM Loading…
3
Pin anthropic<1.0 in the DeepSeek-R1 evaluation requirements
#2669 opened Sep 11, 2026 by 100-JM Loading…
2
Bound and pre-load the DeepSeek-R1 LiveCodeBench grader workers
#2668 opened Sep 11, 2026 by 100-JM Loading…
1
fix: NameError 'has_reranker' in e2e-rag single-shot result display
#2667 opened Sep 9, 2026 by Anai-Guo Loading…
1
fix(TEST01): NameError in verify_performance when the loadgen log reports errors
#2666 opened Sep 9, 2026 by Anai-Guo Loading…
1
Restore IMAGE_EXTENSIONS in the text_to_image FID helper
#2665 opened Sep 3, 2026 by David-Wu1119 Loading…
3
Fix two NameErrors in the e2e-rag reference implementation
#2664 opened Sep 3, 2026 by David-Wu1119 Loading…
3
Fix NameError on every async query in the llama2-70b API SUT
#2663 opened Sep 3, 2026 by David-Wu1119 Loading…
3
Fix three defects in tools/submission/log_parser.py
#2662 opened Sep 3, 2026 by David-Wu1119 Loading…
6
Fix Loadgen Over the Network (LON) Demo
#2647 opened Jul 29, 2026 by mkandes Loading…
1
Remove old submodule
#2594 opened May 26, 2026 by pgmpablo157321 Contributor Loading…
7
Add optional energy efficiency reporting schema for inference benchmarks
#2587 opened May 14, 2026 by hongping-zh Loading…
8
Add PyTorch TorchScript backend for vision benchmarks
#2578 opened Apr 20, 2026 by amd-arsuresh Loading…
2
Add shellcheck to format pass.
#2570 opened Apr 6, 2026 by arav-agarwal2 Contributor Loading…
@pgmpablo157321 @arav-agarwal2
1
Enable llama3.1-8b on CPU
#2567 opened Mar 31, 2026 by cfRod Contributor Loading…
2
Add better logging for performance range mode testing
#2560 opened Mar 11, 2026 by arav-agarwal2 Contributor Loading…
1
Remove shell=True calls across the repo.
#2556 opened Feb 26, 2026 by arav-agarwal2 Contributor Loading…
1
1
Update os.system calls in vision
#2554 opened Feb 26, 2026 by arav-agarwal2 Contributor Loading…
1
feat(llama3.1-8b): expose vLLM engine params as CLI arguments
#2553 opened Feb 26, 2026 by ssaketh-ch Loading…
9
Update submission_checker to use loguru formatting
#2546 opened Feb 23, 2026 by arav-agarwal2 Contributor Loading…
3
Update run_mlperf.py | We should not call FromConfig using audit.conf…
#2541 opened Feb 17, 2026 by arjunsuresh Contributor Loading…
1
Add pre-commit config.
#2536 opened Feb 11, 2026 by arav-agarwal2 Contributor • Draft
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.