mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
55fed1873c
Signed-off-by: h-guo18 <67671475+h-guo18@users.noreply.github.com> Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> Co-authored-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
42 lines
1.5 KiB
JSON
42 lines
1.5 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.transforms.compile-model.backend=torch-simple",
|
|
"--args.attn-page-size=16",
|
|
"--args.transforms.insert-cached-attention.backend=flashinfer",
|
|
"--args.model-factory=AutoModelForCausalLM",
|
|
"--benchmark.enabled=false",
|
|
"--prompt.batch-size=2",
|
|
"--args.model-kwargs.num-hidden-layers=3",
|
|
"--args.model-kwargs.num-attention-heads=32",
|
|
"--prompt.sp-kwargs.max-tokens=128",
|
|
// "--yaml-extra=config.yaml", // uncomment to load a custom extra yaml config file
|
|
// "--dry-run", // uncomment to print the final config and return
|
|
],
|
|
"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
|
|
},
|
|
]
|
|
}
|