3e967dd34a
- Expand GPU specs database to include A100/A800 with Ampere architecture parameters - Rename h200_tester.py to gpu_tester.py for architecture-neutral branding - Add driver/CUDA compatibility validation per GPU generation - Enhance report module with HTML and Markdown output formats - Improve nvbandwidth binary discovery (system paths, DCGM locations) - Add pyproject.toml with uv for dependency management - Update install_deps.sh, configs, and README for multi-architecture support 🤖 Generated with [Qoder][https://qoder.com]
63 lines
1.1 KiB
YAML
63 lines
1.1 KiB
YAML
# GPU type: auto-detect or override to a100/a800/h100/h200/b200/b300
|
|
gpu_type: auto
|
|
|
|
benchmark:
|
|
memory:
|
|
size_mb: 4096
|
|
iterations: 10
|
|
nvbandwidth_buffer_mb: 512
|
|
nvbandwidth_samples: 3
|
|
compute:
|
|
dtypes:
|
|
- fp32
|
|
- tf32
|
|
- fp16
|
|
- bf16
|
|
- fp8
|
|
matrix_size: 4096
|
|
warmup: 10
|
|
iterations: 100
|
|
|
|
health:
|
|
temp_warning: 80
|
|
temp_critical: 90
|
|
power_limit: null # null = auto-detect from GPU TDP per gpu_specs.py
|
|
|
|
nccl:
|
|
min_bandwidth_gbps: null # null = auto-detect (40% of GPU NVLink BW)
|
|
test_allreduce: true
|
|
test_alltoall: true
|
|
test_broadcast: true
|
|
test_reduce_scatter: false
|
|
test_allgather: false
|
|
test_sendrecv: false
|
|
|
|
stress:
|
|
duration_sec: 60
|
|
use_doubles: false
|
|
use_tensor_cores: true
|
|
memory_pct: 90
|
|
gpus: all
|
|
|
|
rdma:
|
|
min_bandwidth_gbps: 50
|
|
max_latency_us: 10
|
|
ib_iterations: 1000
|
|
msg_size: 65536
|
|
ib_device: null
|
|
ib_port: 1
|
|
|
|
training:
|
|
model: gpt2
|
|
batch_size: 8
|
|
seq_length: 2048
|
|
num_steps: 50
|
|
dtype: bf16
|
|
|
|
report:
|
|
output_dir: ./reports
|
|
format: json
|
|
|
|
tools:
|
|
install_dir: /opt/gpu-test-tools
|