TensorRT-LLMs/examples/auto_deploy/model_registry/configs/dashboard_default.yaml
tcherckez-nvidia 56ef97e06e
[#10246][feature] Move AD dashboard to use cudagraph compile backend (#10267)
Signed-off-by: Tal Cherckez <127761168+tcherckez-nvidia@users.noreply.github.com>
2025-12-24 11:09:59 +02:00

10 lines
288 B
YAML

# Default configuration for all AutoDeploy dashboard tests
# These are baseline settings that apply to all models unless overridden
runtime: trtllm
attn_backend: flashinfer
compile_backend: torch-cudagraph
model_factory: AutoModelForCausalLM
skip_loading_weights: false
max_seq_len: 512