mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-25 21:22:57 +08:00
24ac9b5f69
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com> Co-authored-by: Neta Zmora <nzmora@nvidia.com> Co-authored-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
39 lines
1.2 KiB
JSON
39 lines
1.2 KiB
JSON
{
|
|
"version": "0.2.0",
|
|
"configurations": [
|
|
{
|
|
"name": "build_and_run_ad.py",
|
|
"type": "debugpy",
|
|
"request": "launch",
|
|
"program": "build_and_run_ad.py",
|
|
"args": [
|
|
"--model=meta-llama/Meta-Llama-3.1-8B-Instruct",
|
|
"--args.world-size=2",
|
|
"--args.runtime=demollm",
|
|
"--args.compile-backend=torch-simple",
|
|
"--args.attn-page-size=16",
|
|
"--args.attn-backend=flashinfer",
|
|
"--args.model-factory=AutoModelForCausalLM",
|
|
"--benchmark.enabled=false",
|
|
"--prompt.batch-size=2",
|
|
"--args.model-kwargs",
|
|
"num_hidden_layers=3,num_attention_heads=32",
|
|
],
|
|
"console": "integratedTerminal",
|
|
"justMyCode": false,
|
|
"cwd": "${workspaceFolder}/examples/auto_deploy"
|
|
},
|
|
{
|
|
"name": "Python: Debug Tests",
|
|
"type": "debugpy",
|
|
"request": "launch",
|
|
"program": "${file}",
|
|
"purpose": [
|
|
"debug-test",
|
|
],
|
|
"console": "integratedTerminal",
|
|
"justMyCode": false
|
|
},
|
|
]
|
|
}
|