TensorRT-LLM/examples/auto_deploy/.vscode/launch.json at e79eac2f2b8f099acef4cedda0a1ca1773831e0b · NVIDIA/TensorRT-LLM · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
{
    "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",
                "--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
        },
    ]
}