Skip to content

Pull requests: mlcommons/inference

New pull request New
31 Open 1,416 Closed
31 Open 1,416 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

Quick fix: Add user conf to yolo reference implementation
#2446 opened Jan 15, 2026 by pgmpablo157321 Loading…
10
Fixed fps in Wan2.2-T2V-A14B inference script
#2441 opened Jan 14, 2026 by Akshat-Tripathi Loading…
1
Fix DLRMv3 fbgemm_gpu loading with hardcoded Bazel paths
#2439 opened Jan 14, 2026 by ssam18 Loading…
1
3
Update llama2-70b README
#2421 opened Dec 28, 2025 by SamareshSingh Loading…
2
Add accuracy_sample_count
#2414 opened Dec 17, 2025 by v-shobhit Loading…
10
Bandwidth requirement check in submission checker
#2412 opened Dec 16, 2025 by pgmpablo157321 Loading…
1
3
Enable llama3_1-8b reference to run on CPU
#2407 opened Dec 8, 2025 by cfRod Loading…
3
Add enforce_max_duration setting
#2394 opened Nov 21, 2025 by anhappdev Loading…
3
feat(llama2-70b): Add multinode to SUT_API.py for the offline scenario SCC25
#2391 opened Nov 15, 2025 by mrzzy Loading…
1
mlperf submission - clemson SCC25 SCC25
#2387 opened Nov 10, 2025 by TechTyrant • Draft
1
Merge Dev
#2385 opened Nov 4, 2025 by arjunsuresh Loading…
1
Yolo Model Benchmark
#2383 opened Nov 1, 2025 by amitashnanda Loading…
1
LoadGen configuration arguments documentation
#2376 opened Oct 23, 2025 by pgmpablo157321 Loading…
3
Honor the SOURCE_DATE_EPOCH variable
#2345 opened Sep 26, 2025 by hongxu-jia Loading…
2
Add preprocessing documentation for DeepSeek-r1 and Llama3.1-8b
#2270 opened Jul 20, 2025 by anivar Loading…
1
11
Fix off‑by‑one when using --max_examples in language/bert/evaluate_v1.1.py
#2266 opened Jul 18, 2025 by sbite0138 Loading…
2
Added GitHub Actions to Test LLM Accuracy Scripts
#2206 opened Jun 10, 2025 by SridharRambhatla • Draft
12
Fix misleading CUDA device specification by replacing 'cuda:0' with 'cuda'
#2184 opened Apr 26, 2025 by gangula-karthik Loading…
1
Fix for dataset path with space
#2183 opened Apr 23, 2025 by anandhu-eng Loading…
5
Fix for Recognizing --threads Option in Benchmarking
#2161 opened Mar 28, 2025 by sujik18 Loading…
11
Add automotive benchmarking setting after v5.0
#2139 opened Feb 26, 2025 by pgmpablo157321 Loading…
1
All merged branch from #1934-#1931
#1940 opened Nov 19, 2024 by zixianwang2022 Loading…
3
MigraphX version of reference code
#1516 opened Nov 12, 2023 by mrmhodak Loading…
1
Fix SingleStream and MultiStream reciprocal score comparison for TEST04
#1491 opened Sep 11, 2023 by sahelib25 Loading…
1
12
Update loadgen.cc
#1334 opened Feb 16, 2023 by yin1112 Loading…
2
ProTip! Exclude everything labeled bug with -label:bug.