8 × NVIDIA RTX PRO 6000 Blackwell Server Edition

Tested system

Processor: Intel(R) Xeon(R) 6767P
Graphics: NVIDIA RTX PRO 6000 Blackwell Server Edition
Accelerator count: 8
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 / llama2-70b-99.9Offline · v6.1 · Tokens/s

8 × NVIDIA RTX PRO 6000 Blackwell Server Edition

29,796.70^* Tokens/s

Accuracy target / result: ROUGE1: 44.7408 ROUGE2: 22.3357 ROUGEL: 29.1354 TOKENS_PER_SAMPLE: 274.4
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Operating system: Ubuntu 24.04

MLPerf Inference / llama2-70b-99.9Server · v6.1 · Tokens/s

8 × NVIDIA RTX PRO 6000 Blackwell Server Edition

28,973.30^* Tokens/s

Accuracy target / result: ROUGE1: 44.6929 ROUGE2: 22.2906 ROUGEL: 29.0805 TOKENS_PER_SAMPLE: 267.3
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Operating system: Ubuntu 24.04

Processing & platform

Processor: Intel(R) Xeon(R) 6767P
Graphics: NVIDIA RTX PRO 6000 Blackwell Server Edition

Connectivity & software

Operating system: Ubuntu 24.04

System configuration

Reported host core count: 64
Processors per node: 2
Accelerator count: 8
Nodes: 1
Software stack: TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Submission division: closed

* Provisional data