8 × AMD Instinct MI355X 288GB HBM3e

Tested system

Processor: AMD EPYC 9575F
Graphics: AMD Instinct MI355X 288GB HBM3e
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 / gpt-oss-120bOffline · v6.1 · Tokens/s

8 × AMD Instinct MI355X 288GB HBM3e

115,567^* Tokens/s

Accuracy target / result: exact_match: 83.895
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: vLLM 0.22.0, PyTorch 2.10.0, ROCm 7.2.2
Operating system: Ubuntu 22.04.2 LTS (kernel 5.15.0-70-generic)

MLPerf Inference / gpt-oss-120bServer · v6.1 · Tokens/s

8 × AMD Instinct MI355X 288GB HBM3e

109,083^* Tokens/s

Accuracy target / result: exact_match: 83.679
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: vLLM 0.22.0, PyTorch 2.10.0, ROCm 7.2.2
Operating system: Ubuntu 22.04.2 LTS (kernel 5.15.0-70-generic)

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

8 × AMD Instinct MI355X 288GB HBM3e

101,553^* Tokens/s

Accuracy target / result: ROUGE1: 44.5168 ROUGE2: 22.1764 ROUGEL: 28.9174 TOKENS_PER_SAMPLE: 284.5
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: vLLM 0.22.0, PyTorch 2.10.0, ROCm 7.2.2
Operating system: Ubuntu 22.04.2 LTS (kernel 5.15.0-70-generic)

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

8 × AMD Instinct MI355X 288GB HBM3e

100,392^* Tokens/s

Accuracy target / result: ROUGE1: 44.5335 ROUGE2: 22.1719 ROUGEL: 28.9333 TOKENS_PER_SAMPLE: 284.1
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: vLLM 0.22.0, PyTorch 2.10.0, ROCm 7.2.2
Operating system: Ubuntu 22.04.2 LTS (kernel 5.15.0-70-generic)

MLPerf Inference / llama3.1-8bOffline · v6.1 · Tokens/s

8 × AMD Instinct MI355X 288GB HBM3e

144,321^* Tokens/s

Accuracy target / result: ROUGE1: 38.5632 ROUGE2: 16.0256 ROUGEL: 24.4374 ROUGELSUM: 35.7022 GEN_LEN: 8150941
Weight precision: fp8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: vLLM 0.22.0, PyTorch 2.10.0, ROCm 7.2.2
Operating system: Ubuntu 22.04.2 LTS (kernel 5.15.0-70-generic)

MLPerf Inference / llama3.1-8bServer · v6.1 · Tokens/s

8 × AMD Instinct MI355X 288GB HBM3e

148,594^* Tokens/s

Accuracy target / result: ROUGE1: 38.5373 ROUGE2: 16.018 ROUGEL: 24.4335 ROUGELSUM: 35.6767 GEN_LEN: 8166290
Weight precision: fp8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: vLLM 0.22.0, PyTorch 2.10.0, ROCm 7.2.2
Operating system: Ubuntu 22.04.2 LTS (kernel 5.15.0-70-generic)

MLPerf Inference / wan-2.2-t2v-a14bOffline · v6.1 · Samples/s

8 × AMD Instinct MI355X 288GB HBM3e

0.07^* Samples/s

Accuracy target / result: vbench_score: 69.9515
Weight precision: bf16, fp8, fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: vLLM 0.22.0, PyTorch 2.10.0, ROCm 7.2.2
Operating system: Ubuntu 22.04.2 LTS (kernel 5.15.0-70-generic)

MLPerf Inference / wan-2.2-t2v-a14bSingleStream · v6.1 · Latency (s)

8 × AMD Instinct MI355X 288GB HBM3e

16.33^* Latency (s)

Accuracy target / result: vbench_score: 70.3415
Weight precision: bf16, fp8, fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: vLLM 0.22.0, PyTorch 2.10.0, ROCm 7.2.2
Operating system: Ubuntu 22.04.2 LTS (kernel 5.15.0-70-generic)

Processing & platform

Processor: AMD EPYC 9575F
Graphics: AMD Instinct MI355X 288GB HBM3e

Connectivity & software

Operating system: Ubuntu 22.04.2 LTS (kernel 5.15.0-70-generic)

System configuration

Reported host core count: 64
Processors per node: 2
Accelerator count: 8
Nodes: 1
Software stack: vLLM 0.22.0, PyTorch 2.10.0, ROCm 7.2.2
Submission division: closed

* Provisional data