mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-04 18:21:52 +08:00
10 lines
288 B
YAML
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
|