Intel(R) Xeon(R) 6787P

Tested system

Processor: Intel(R) Xeon(R) 6787P
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) 6787P

1,189.89^* Tokens/s

Accuracy target / result: ROUGE1: 38.7008 ROUGE2: 15.8479 ROUGEL: 24.4355 ROUGELSUM: 35.7034 GEN_LEN: 8193707
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 86
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: Ubuntu 24.04.3

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

Intel(R) Xeon(R) 6787P

516.06^* Tokens/s

Accuracy target / result: ROUGE1: 38.7059 ROUGE2: 15.8614 ROUGEL: 24.4785 ROUGELSUM: 35.726 GEN_LEN: 8175493
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 86
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: Ubuntu 24.04.3

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

Intel(R) Xeon(R) 6787P

13,273.70^* Samples/s

Accuracy target / result: acc: 72.520
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 86
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: Ubuntu 24.04.3

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

Intel(R) Xeon(R) 6787P

1,477.40^* Samples/s

Accuracy target / result: ACCURACY: 97.89045996917045
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 86
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: Ubuntu 24.04.3

Processing & platform

Processor: Intel(R) Xeon(R) 6787P

Connectivity & software

Operating system: Ubuntu 24.04.3

System configuration

Reported host core count: 86
Processors per node: 2
Accelerator count: 0
Nodes: 1
Software stack: PyTorch
Submission division: closed

* Provisional data