80 lines
3.8 KiB
JSON
80 lines
3.8 KiB
JSON
{
|
|
"status": "exited",
|
|
"pid": 52656,
|
|
"start": 1790060589.375201,
|
|
"jobs": [
|
|
{
|
|
"name": "spark-cuda-wsl",
|
|
"command": [
|
|
"wsl",
|
|
"-d",
|
|
"Ubuntu",
|
|
"--",
|
|
"bash",
|
|
"-lc",
|
|
"cd /home/zhout/project/edge_infer/vllm-omni-edge && PYTHONPATH=. HF_HUB_OFFLINE=1 VLLM_USE_FLASHINFER_SAMPLER=0 VLLM_WSL2_ENABLE_PIN_MEMORY=1 CUDA_HOME=/home/zhout/project/edge_infer/.venvs/omni-cuda-029/lib/python3.12/site-packages/nvidia/cu13 PATH=/home/zhout/project/edge_infer/.venvs/omni-cuda-029/lib/python3.12/site-packages/nvidia/cu13/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/lib/wsl/lib timeout 10800 ../.venvs/omni-cuda-029/bin/python benchmarks/edge_harness/profile_local_text.py --model ../models/Spark-X2.5-4B --out ../analysis/experiments/e2e_profiling_20260922/spark-cuda-wsl"
|
|
],
|
|
"status": "exited",
|
|
"start": 1790060589.378202,
|
|
"returncode": 0,
|
|
"end": 1790062795.1474967,
|
|
"benchmark_status": "completed",
|
|
"error": null
|
|
},
|
|
{
|
|
"name": "spark-cuda-windows",
|
|
"command": [
|
|
"C:\\Users\\zhout\\w2\\omni029venv\\Scripts\\python.exe",
|
|
"\\\\wsl.localhost\\Ubuntu\\home\\zhout\\project\\edge_infer\\vllm-omni-edge\\benchmarks\\edge_harness\\profile_local_text.py",
|
|
"--model",
|
|
"\\\\wsl.localhost\\Ubuntu\\home\\zhout\\project\\edge_infer\\models\\Spark-X2.5-4B",
|
|
"--out",
|
|
"\\\\wsl.localhost\\Ubuntu\\home\\zhout\\project\\edge_infer\\analysis\\experiments\\e2e_profiling_20260922\\spark-cuda-windows"
|
|
],
|
|
"status": "exited",
|
|
"start": 1790065913.5339177,
|
|
"returncode": 0,
|
|
"end": 1790068263.0289257,
|
|
"benchmark_status": "completed",
|
|
"error": null,
|
|
"retry_reason": "Corrected native CUDA runtime DLL setting; prior attempt archived"
|
|
},
|
|
{
|
|
"name": "tts-cuda-wsl",
|
|
"command": [
|
|
"wsl",
|
|
"-d",
|
|
"Ubuntu",
|
|
"--",
|
|
"bash",
|
|
"-lc",
|
|
"cd /home/zhout/project/edge_infer/vllm-omni-edge && PYTHONPATH=. HF_HUB_OFFLINE=1 VLLM_USE_FLASHINFER_SAMPLER=0 VLLM_WSL2_ENABLE_PIN_MEMORY=1 CUDA_HOME=/home/zhout/project/edge_infer/.venvs/omni-cuda-029/lib/python3.12/site-packages/nvidia/cu13 PATH=/home/zhout/project/edge_infer/.venvs/omni-cuda-029/lib/python3.12/site-packages/nvidia/cu13/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/lib/wsl/lib timeout 10800 ../.venvs/omni-cuda-029/bin/python benchmarks/edge_harness/profile_local_tts.py --model /home/zhout/.cache/huggingface/hub/models--Qwen--Qwen3-TTS-12Hz-0.6B-CustomVoice/snapshots/85e237c12c027371202489a0ec509ded67b5e4b5 --out ../analysis/experiments/e2e_profiling_20260922/tts-cuda-wsl"
|
|
],
|
|
"status": "exited",
|
|
"start": 1790062812.6633985,
|
|
"returncode": 0,
|
|
"end": 1790065331.9386182,
|
|
"benchmark_status": "completed",
|
|
"error": null
|
|
},
|
|
{
|
|
"name": "tts-cuda-windows",
|
|
"command": [
|
|
"C:\\Users\\zhout\\w2\\omni029venv\\Scripts\\python.exe",
|
|
"\\\\wsl.localhost\\Ubuntu\\home\\zhout\\project\\edge_infer\\vllm-omni-edge\\benchmarks\\edge_harness\\profile_local_tts.py",
|
|
"--model",
|
|
"C:\\Users\\zhout\\w2\\models\\Qwen3-TTS-0.6B-85e237c",
|
|
"--out",
|
|
"\\\\wsl.localhost\\Ubuntu\\home\\zhout\\project\\edge_infer\\analysis\\experiments\\e2e_profiling_20260922\\tts-cuda-windows"
|
|
],
|
|
"status": "exited",
|
|
"start": 1790065331.9426181,
|
|
"returncode": 0,
|
|
"end": 1790065913.1483374,
|
|
"benchmark_status": "failed",
|
|
"error": "PermissionError(13, '\u62d2\u7edd\u8bbf\u95ee\u3002')"
|
|
}
|
|
],
|
|
"end": 1790068263.0289257,
|
|
"note": "Includes serial native Spark launcher correction before traces."
|
|
} |