embeddinggemma-2-GGUF / TIMINGS.json
homerquan's picture
Record published Docker pull and multimodal validation
d122027 verified
Raw History Blame Contribute Delete
10.3 kB
[
{
"stage": "download",
"command": [
"python3",
"scripts/download_source.py"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:55:21.409343+00:00",
"finished_utc": "2026-11-01T14:55:53.401870+00:00",
"elapsed_seconds": 31.99252673998126,
"returncode": 0
},
{
"stage": "build-configure",
"command": [
"cmake",
"-S",
"llama.cpp",
"-B",
"llama.cpp/build",
"-DCMAKE_BUILD_TYPE=Release",
"-DGGML_CUDA=OFF",
"-DGGML_NATIVE=ON",
"-DLLAMA_BUILD_TESTS=OFF",
"-DLLAMA_CURL=OFF"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:55:46.632685+00:00",
"finished_utc": "2026-11-01T14:55:48.362987+00:00",
"elapsed_seconds": 1.73029996099649,
"returncode": 0
},
{
"stage": "build",
"command": [
"cmake",
"--build",
"llama.cpp/build",
"--config",
"Release",
"-j",
"16",
"--target",
"llama-quantize",
"llama-server"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:55:48.380276+00:00",
"finished_utc": "2026-11-01T14:56:48.044752+00:00",
"elapsed_seconds": 59.66447541900561,
"returncode": 0
},
{
"stage": "dependencies",
"command": [
".venv/bin/python",
"-m",
"pip",
"install",
"-r",
"llama.cpp/requirements/requirements-convert_hf_to_gguf.txt",
"huggingface_hub>=0.34.0,<1.0"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:55:49.275061+00:00",
"finished_utc": "2026-11-01T14:56:14.893959+00:00",
"elapsed_seconds": 25.618897876003757,
"returncode": 0
},
{
"stage": "dmr-image-pull",
"command": [
"docker",
"pull",
"docker/model-runner@sha256:9967b6c1092ff01e7cf68119ab25067a1f58e3d1b06873bc16fe1e758bcd914f"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:56:23.532588+00:00",
"finished_utc": "2026-11-01T14:56:27.210774+00:00",
"elapsed_seconds": 3.6781821949989535,
"returncode": 0
},
{
"stage": "convert-bf16",
"command": [
".venv/bin/python",
"llama.cpp/convert_hf_to_gguf.py",
"source",
"--outtype",
"bf16",
"--model-name",
"embeddinggemma-2",
"--outfile",
"work/embeddinggemma-2-BF16.gguf"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:56:49.790088+00:00",
"finished_utc": "2026-11-01T14:56:53.358771+00:00",
"elapsed_seconds": 3.5686840260168537,
"returncode": 1
},
{
"stage": "convert-mmproj",
"command": [
".venv/bin/python",
"llama.cpp/convert_hf_to_gguf.py",
"source",
"--mmproj",
"--outtype",
"q8_0",
"--model-name",
"embeddinggemma-2",
"--outfile",
"release/mmproj-embeddinggemma-2-Q8_0.gguf"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:56:50.417675+00:00",
"finished_utc": "2026-11-01T14:56:53.964458+00:00",
"elapsed_seconds": 3.54678301900276,
"returncode": 0
},
{
"stage": "cuda-configure",
"command": [
"cmake",
"-S",
"llama.cpp",
"-B",
"llama.cpp/build-cuda",
"-DCMAKE_BUILD_TYPE=Release",
"-DGGML_CUDA=ON",
"-DCMAKE_CUDA_ARCHITECTURES=121",
"-DGGML_NATIVE=ON",
"-DLLAMA_BUILD_TESTS=OFF",
"-DLLAMA_CURL=OFF"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:57:33.645338+00:00",
"finished_utc": "2026-11-01T14:57:36.272337+00:00",
"elapsed_seconds": 2.626998322986765,
"returncode": 0
},
{
"stage": "cuda-build",
"command": [
"cmake",
"--build",
"llama.cpp/build-cuda",
"--config",
"Release",
"-j",
"8",
"--target",
"llama-server"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:57:36.303210+00:00",
"finished_utc": "2026-11-01T15:01:19.019507+00:00",
"elapsed_seconds": 222.71629584900802,
"returncode": 0
},
{
"stage": "convert-bf16-compatible",
"command": [
".venv/bin/python",
"scripts/convert_compatible.py",
"source",
"--outtype",
"bf16",
"--model-name",
"embeddinggemma-2",
"--outfile",
"work/embeddinggemma-2-BF16.gguf"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:58:26.671428+00:00",
"finished_utc": "2026-11-01T14:58:39.271335+00:00",
"elapsed_seconds": 12.599901882989798,
"returncode": 0
},
{
"stage": "quantize",
"command": [
"llama.cpp/build/bin/llama-quantize",
"work/embeddinggemma-2-BF16.gguf",
"release/embeddinggemma-2-Q4_K_M.gguf",
"Q4_K_M"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:59:03.341119+00:00",
"finished_utc": "2026-11-01T14:59:05.780096+00:00",
"elapsed_seconds": 2.438970130024245,
"returncode": 0
},
{
"stage": "audit",
"command": [
".venv/bin/python",
"scripts/audit_gguf.py"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T14:59:48.642886+00:00",
"finished_utc": "2026-11-01T15:00:09.839507+00:00",
"elapsed_seconds": 21.196617795998463,
"returncode": 1
},
{
"stage": "audit-final",
"command": [
".venv/bin/python",
"scripts/audit_gguf.py"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:00:53.569576+00:00",
"finished_utc": "2026-11-01T15:01:15.285176+00:00",
"elapsed_seconds": 21.71559885001625,
"returncode": 0
},
{
"stage": "validate-bf16",
"command": [
".venv/bin/python",
"scripts/validate_bf16.py"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:01:15.314013+00:00",
"finished_utc": "2026-11-01T15:01:17.519620+00:00",
"elapsed_seconds": 2.2056051869876683,
"returncode": 0
},
{
"stage": "dmr-start",
"command": [
"bash",
"scripts/start_validation_runner.sh"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:02:00.812758+00:00",
"finished_utc": "2026-11-01T15:02:01.138690+00:00",
"elapsed_seconds": 0.32593187599559315,
"returncode": 0
},
{
"stage": "dmr-package",
"command": [
"env",
"MODEL_RUNNER_HOST=http://127.0.0.1:12435",
"docker",
"model",
"package",
"--gguf",
"$TASK_ROOT/release/embeddinggemma-2-Q4_K_M.gguf",
"--mmproj",
"$TASK_ROOT/release/mmproj-embeddinggemma-2-Q8_0.gguf",
"--license",
"$TASK_ROOT/release/LICENSE",
"--context-size",
"2048",
"mirrorneuronlab/embeddinggemma-2:q4_k_m"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:02:13.051800+00:00",
"finished_utc": "2026-11-01T15:02:15.412325+00:00",
"elapsed_seconds": 2.3605253199930303,
"returncode": 0
},
{
"stage": "validate-dmr",
"command": [
".venv/bin/python",
"scripts/validate_dmr.py"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:02:15.594479+00:00",
"finished_utc": "2026-11-01T15:02:17.820825+00:00",
"elapsed_seconds": 2.226341144007165,
"returncode": 0
},
{
"stage": "dmr-run",
"command": [
"env",
"MODEL_RUNNER_HOST=http://127.0.0.1:12435",
"docker",
"model",
"run",
"--detach",
"mirrorneuronlab/embeddinggemma-2:q4_k_m"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:05:52.619080+00:00",
"finished_utc": "2026-11-01T15:05:52.670364+00:00",
"elapsed_seconds": 0.0512839280127082,
"returncode": 0
},
{
"stage": "prepare-release",
"command": [
".venv/bin/python",
"scripts/prepare_release.py"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:08:32.554817+00:00",
"finished_utc": "2026-11-01T15:08:34.530224+00:00",
"elapsed_seconds": 1.9754067820031196,
"returncode": 0
},
{
"stage": "hf-publish",
"command": [
".venv/bin/python",
"scripts/publish_release.py"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:09:08.040337+00:00",
"finished_utc": "2026-11-01T15:09:09.418174+00:00",
"elapsed_seconds": 1.3778367980266921,
"returncode": 1
},
{
"stage": "hf-publish-retry",
"command": [
"env",
"HF_HOME=$TASK_ROOT/work/hf-home",
"HF_HUB_CACHE=$TASK_ROOT/work/hf-cache",
"HF_XET_CACHE=$TASK_ROOT/work/xet-cache",
"HF_HUB_DISABLE_XET=1",
".venv/bin/python",
"scripts/publish_release.py"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:09:46.128486+00:00",
"finished_utc": "2026-11-01T15:10:00.651670+00:00",
"elapsed_seconds": 14.523182463977719,
"returncode": 0
},
{
"stage": "hf-verify-public",
"command": [
".venv/bin/python",
"scripts/verify_published.py"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:10:32.802376+00:00",
"finished_utc": "2026-11-01T15:10:34.731406+00:00",
"elapsed_seconds": 1.9290308729978278,
"returncode": 0
},
{
"stage": "hf-dmr-pull",
"command": [
"env",
"MODEL_RUNNER_HOST=http://127.0.0.1:12435",
"docker",
"model",
"pull",
"hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:10:33.079233+00:00",
"finished_utc": "2026-11-01T15:10:41.337838+00:00",
"elapsed_seconds": 8.258602988003986,
"returncode": 0
},
{
"stage": "hf-dmr-run",
"command": [
"env",
"MODEL_RUNNER_HOST=http://127.0.0.1:12435",
"docker",
"model",
"run",
"--detach",
"hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:10:41.357601+00:00",
"finished_utc": "2026-11-01T15:10:42.909069+00:00",
"elapsed_seconds": 1.5514679400075693,
"returncode": 0
},
{
"stage": "hf-validate-dmr",
"command": [
".venv/bin/python",
"scripts/validate_dmr.py",
"--model",
"hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:10:42.925462+00:00",
"finished_utc": "2026-11-01T15:10:44.951753+00:00",
"elapsed_seconds": 2.026292441994883,
"returncode": 0
}
]