Collection/NVIDIA/NVIDIA 8 × H200 — MLPerf v4.1 Mixtral

VLSI MUSEUM / ENGINEERING RECORD2024

NVIDIAAI benchmark systems

system

The engineering record starts here.

We have not yet identified a reliable public die photograph for this record. Its identity and documented evidence remain open to explore.

SYSTEM / 2024

NVIDIA 8 × H200 — MLPerf v4.1 Mixtral

A measured eight-GPU system submission for the MLPerf Inference v4.1 Offline Mixtral workload. It is a submitter-reported benchmark, not an independent review or single-chip performance.

NVIDIAAI benchmark systems

Research connections

CompanyNVIDIA ↗

Specifications

9 SOURCE-LINKED FIELDS

Benchmark	Manufacturer / primary sourceNVIDIA Scope: Eight-GPU benchmark system Conditions: MLPerf Inference v4.1; Closed/Data Center/Offline; Mixtral 8x7B; eight GPUs; TensorRT-LLM, extensive FP8 use. MoE 8 experts/2 active; not structured 2:4 sparsity. Submitted 4.1-0048. Result date 2024-08-28. Source date: 2024-08-28
Workload	Manufacturer / primary sourceNVIDIA Scope: Eight-GPU benchmark system Conditions: MLPerf Inference v4.1; Closed/Data Center/Offline; Mixtral 8x7B; eight GPUs; TensorRT-LLM, extensive FP8 use. MoE 8 experts/2 active; not structured 2:4 sparsity. Submitted 4.1-0048. Result date 2024-08-28. Source date: 2024-08-28
Scenario	Manufacturer / primary sourceNVIDIA Scope: Eight-GPU benchmark system Conditions: MLPerf Inference v4.1; Closed/Data Center/Offline; Mixtral 8x7B; eight GPUs; TensorRT-LLM, extensive FP8 use. MoE 8 experts/2 active; not structured 2:4 sparsity. Submitted 4.1-0048. Result date 2024-08-28. Source date: 2024-08-28
Accelerator	Manufacturer / primary sourceNVIDIA Scope: Eight-GPU benchmark system Conditions: MLPerf Inference v4.1; Closed/Data Center/Offline; Mixtral 8x7B; eight GPUs; TensorRT-LLM, extensive FP8 use. MoE 8 experts/2 active; not structured 2:4 sparsity. Submitted 4.1-0048. Result date 2024-08-28. Source date: 2024-08-28
Accelerator count	Manufacturer / primary sourceNVIDIA Scope: Eight-GPU benchmark system Conditions: MLPerf Inference v4.1; Closed/Data Center/Offline; Mixtral 8x7B; eight GPUs; TensorRT-LLM, extensive FP8 use. MoE 8 experts/2 active; not structured 2:4 sparsity. Submitted 4.1-0048. Result date 2024-08-28. Source date: 2024-08-28
Measured throughput	Manufacturer / primary sourceNVIDIA Scope: Eight-GPU benchmark system Conditions: MLPerf Inference v4.1; Closed/Data Center/Offline; Mixtral 8x7B; eight GPUs; TensorRT-LLM, extensive FP8 use. MoE 8 experts/2 active; not structured 2:4 sparsity. Submitted 4.1-0048. Result date 2024-08-28. Source date: 2024-08-28
Numerical format	Manufacturer / primary sourceNVIDIA Scope: Eight-GPU benchmark system Conditions: MLPerf Inference v4.1; Closed/Data Center/Offline; Mixtral 8x7B; eight GPUs; TensorRT-LLM, extensive FP8 use. MoE 8 experts/2 active; not structured 2:4 sparsity. Submitted 4.1-0048. Result date 2024-08-28. Source date: 2024-08-28
Software	Manufacturer / primary sourceNVIDIA Scope: Eight-GPU benchmark system Conditions: MLPerf Inference v4.1; Closed/Data Center/Offline; Mixtral 8x7B; eight GPUs; TensorRT-LLM, extensive FP8 use. MoE 8 experts/2 active; not structured 2:4 sparsity. Submitted 4.1-0048. Result date 2024-08-28. Source date: 2024-08-28
Configured accelerator TDP	Manufacturer / primary sourceNVIDIA Scope: Eight-GPU benchmark system Source date: 2024-08-28

THE VISUAL EVIDENCE

Visual sources

0 DOCUMENTED SOURCES

Help document this silicon.

We have not yet identified a reliable public visual source for this record. Suggest a die photograph, package image, paper or manufacturer diagram.

Record identity & scope

system · NVIDIA 8 × H200 — MLPerf v4.1 Mixtral

4.1-0048 Mixtral 8x7B