Intel(R) Xeon(R) 6980P

Tested system

Processor: Intel(R) Xeon(R) 6980P
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) 6980P

1,916.74^* Tokens/s

Accuracy target / result: ROUGE1: 38.6418 ROUGE2: 15.8693 ROUGEL: 24.4809 ROUGELSUM: 35.6703 GEN_LEN: 8194131
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 128
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: CentOS Stream 9

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

Intel(R) Xeon(R) 6980P

1,139.51^* Tokens/s

Accuracy target / result: ROUGE1: 38.6681 ROUGE2: 15.9242 ROUGEL: 24.5144 ROUGELSUM: 35.7046 GEN_LEN: 8206137
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 128
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: CentOS Stream 9

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

Intel(R) Xeon(R) 6980P

24,573.70^* Samples/s

Accuracy target / result: acc: 72.541
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 128
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: CentOS Stream 9

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

Intel(R) Xeon(R) 6980P

2,319.02^* Samples/s

Accuracy target / result: ACCURACY: 97.89143156192017
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 128
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: CentOS Stream 9

Processing & platform

Processor: Intel(R) Xeon(R) 6980P

Connectivity & software

Operating system: CentOS Stream 9

System configuration

Reported host core count: 128
Processors per node: 2
Accelerator count: 0
Nodes: 1
Software stack: PyTorch
Submission division: closed

* Provisional data