Intel(R) Xeon(R) 6972P

Tested system

Processor: Intel(R) Xeon(R) 6972P
Accelerator count: 0
Nodes: 1

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

MLPerf Inference / llama3_1-8bOffline · v6.1 · Tokens/s

Intel(R) Xeon(R) 6972P

1,507.21^* Tokens/s

Accuracy target / result: ROUGE1: 38.7872 ROUGE2: 16.0024 ROUGEL: 24.5918 ROUGELSUM: 35.7668 GEN_LEN: 8190420
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 96
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: RHEL 9.9

MLPerf Inference / llama3_1-8bServer · v6.1 · Tokens/s

Intel(R) Xeon(R) 6972P

644.79^* Tokens/s

Accuracy target / result: ROUGE1: 38.606 ROUGE2: 15.7593 ROUGEL: 24.3946 ROUGELSUM: 35.6342 GEN_LEN: 8185295
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 96
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: RHEL 9.9

MLPerf Inference / whisperOffline · v6.1 · Samples/s

Intel(R) Xeon(R) 6972P

1,966.11^* Samples/s

Accuracy target / result: ACCURACY: 97.86193444026833
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 96
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: RHEL 9.9

Processing & platform

Processor: Intel(R) Xeon(R) 6972P

Connectivity & software

Operating system: RHEL 9.9

System configuration

Reported host core count: 96
Processors per node: 2
Accelerator count: 0
Nodes: 1
Software stack: PyTorch
Submission division: closed

* Provisional data