SOTA: MLPerf inference benchmark v0.5 results snapshot (open, Research, Development, and Other) for collaborative validation
result:sota-mlperf-inference-results-v0.5-open-rdo (v1.0.0)
Please report if this CK component works: 1 ▲
or fails: 0 ▲
Live CK scoreboards are connected with portable CK workflows
and adaptive containers to help the community participate in collaborative AI/ML/SW/HW benchmarking and DSE.
See this paper and ACM TechTalk for more details.
Benchmark results (performance): P_*_SS - Single Stream in milliseconds, P_*_MS - MultiStream in no. streams, P_*_S - Server in QPS, P_*_O - Offline in inputs/second.
Benchmark results (accuracy): A_IC* - Top-1, A_OD* - mAP, A_NMT* - BLEU.
cK components: packages, software detection plugins.
Image Classification: IC1 - ImageNet, MobileNet-v1, IC2 - ImageNet, ResNet-50 v1.5.
Object detection: OD1 - COCO, SSD w/ MobileNet-v1, OD2 - COCO 1200x1200, SSD w/ ResNet-34.
Translation: NMT - WMT E-G, NMT.
Form Factor: FF_M - Mobile/Handheld, FF_D - Desktop/Workstation, FF_S - Server, FF_E - Edge/Embedded.
These are not official results but a snapshot to collaboratively reproduce results and add portable workflows!
MLPerf name and logo are trademarks. See www.mlperf.org for more information.
Reproduced paper: MLPerf Inference Benchmark
Related reusable solutions:
1
2
3
4
5
6
7
SOTA: MLPerf inference benchmark v0.5 results snapshot (open, Research, Development, and Other) for collaborative validation
Please log in to add your comments!
If you notice any inapropriate content that should not be here, please report us as soon as possible and we will try to remove it within 48 hours!