@@ -201,8 +201,8 @@ jobs:
201201 echo "Success: prefill ($PROMPT_TOKENS tokens) + decode completed"
202202 echo "::endgroup::"
203203
204- export -model-metal-artifact :
205- name : export -model-metal-artifact
204+ test -model-metal-e2e :
205+ name : test -model-metal-e2e
206206 # Skip this job if the pull request is from a fork (HuggingFace secrets are not available).
207207 # Path-filtered on push: mirrors the workflow-level pull_request `paths:`
208208 # filter so push commits that don't touch metal-relevant paths skip
@@ -251,10 +251,33 @@ jobs:
251251 ref : ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
252252 timeout : 90
253253 secrets-env : EXECUTORCH_HF_TOKEN
254- upload-artifact : ${{ matrix.model.repo }}-${{ matrix.model.name }}-metal-${{ matrix.quant }}
255254 script : |
256255 set -eux
257256
257+ echo "::group::Print machine info"
258+ uname -a
259+ if [ $(uname -s) == Darwin ]; then
260+ sw_vers
261+ # Print RAM in GB
262+ RAM_BYTES=$(sysctl -n hw.memsize)
263+ RAM_GB=$(echo "scale=2; $RAM_BYTES/1024/1024/1024" | bc)
264+ echo "Available RAM (GB): $RAM_GB"
265+ sysctl machdep.cpu.brand_string
266+ sysctl machdep.cpu.core_count
267+ # Print number of GPU cores (Apple Silicon)
268+ if command -v system_profiler &> /dev/null; then
269+ GPU_CORES=$(system_profiler SPDisplaysDataType | awk '/Total Number of Cores/ {print $5; exit}')
270+ if [ -z "$GPU_CORES" ]; then
271+ # Fallback: try to parse "Core Count" from Apple GPU section
272+ GPU_CORES=$(system_profiler SPDisplaysDataType | awk '/Core Count/ {print $3; exit}')
273+ fi
274+ echo "GPU Cores: ${GPU_CORES:-Unknown}"
275+ else
276+ echo "system_profiler not available, cannot determine GPU cores."
277+ fi
278+ fi
279+ echo "::endgroup::"
280+
258281 echo "::group::Setup Huggingface"
259282 ${CONDA_RUN} pip install -U "huggingface_hub[cli]<1.0" accelerate
260283 ${CONDA_RUN} huggingface-cli login --token $SECRET_EXECUTORCH_HF_TOKEN
@@ -284,87 +307,7 @@ jobs:
284307 if [ "${{ matrix.model.name }}" = "Voxtral-Mini-4B-Realtime-2602" ]; then
285308 VR_MODE="vr-offline"
286309 fi
287- ${CONDA_RUN} bash .ci/scripts/export_model_artifact.sh metal "${{ matrix.model.repo }}/${{ matrix.model.name }}" "${{ matrix.quant }}" "${RUNNER_ARTIFACT_DIR}" "${VR_MODE}"
288-
289- test-model-metal-e2e :
290- name : test-model-metal-e2e
291- # Same path filter as export-model-metal-artifact above. Also
292- # explicitly gated on the export job succeeding — when needs: jobs
293- # are *skipped* (e.g. fork PR), GitHub still evaluates this if:,
294- # so without the explicit success-check this job would run and then
295- # fail trying to download an artifact that was never produced.
296- needs : [changed-files, export-model-metal-artifact, run-decision]
297- if : |
298- needs.export-model-metal-artifact.result == 'success' &&
299- (
300- contains(needs.changed-files.outputs.changed-files, 'backends/apple/metal') ||
301- contains(needs.changed-files.outputs.changed-files, 'backends/aoti') ||
302- contains(needs.changed-files.outputs.changed-files, 'examples/models/qwen3_5_moe') ||
303- contains(needs.changed-files.outputs.changed-files, 'extension/llm/export') ||
304- contains(needs.changed-files.outputs.changed-files, '.github/workflows/metal.yml') ||
305- needs.run-decision.outputs.is-full-run == 'true'
306- )
307- uses : pytorch/test-infra/.github/workflows/macos_job.yml@main
308- strategy :
309- fail-fast : false
310- matrix :
311- model :
312- - repo : " mistralai"
313- name : " Voxtral-Mini-3B-2507"
314- - repo : " mistralai"
315- name : " Voxtral-Mini-4B-Realtime-2602"
316- - repo : " openai"
317- name : " whisper-small"
318- - repo : " openai"
319- name : " whisper-large-v3-turbo"
320- - repo : " nvidia"
321- name : " parakeet-tdt"
322- quant :
323- - " non-quantized"
324- - " quantized-int4-metal"
325- exclude :
326- # Exclude non-quantized for Voxtral Realtime (too large)
327- - model :
328- repo : " mistralai"
329- name : " Voxtral-Mini-4B-Realtime-2602"
330- quant : " non-quantized"
331- with :
332- default-packages : " "
333- runner : macos-m2-stable
334- python-version : ' 3.11'
335- submodules : ' recursive'
336- ref : ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
337- timeout : 90
338- download-artifact : ${{ matrix.model.repo }}-${{ matrix.model.name }}-metal-${{ matrix.quant }}
339- script : |
340- set -eux
341-
342- echo "::group::Print machine info"
343- uname -a
344- if [ $(uname -s) == Darwin ]; then
345- sw_vers
346- # Print RAM in GB
347- RAM_BYTES=$(sysctl -n hw.memsize)
348- RAM_GB=$(echo "scale=2; $RAM_BYTES/1024/1024/1024" | bc)
349- echo "Available RAM (GB): $RAM_GB"
350- sysctl machdep.cpu.brand_string
351- sysctl machdep.cpu.core_count
352- # Print number of GPU cores (Apple Silicon)
353- if command -v system_profiler &> /dev/null; then
354- GPU_CORES=$(system_profiler SPDisplaysDataType | awk '/Total Number of Cores/ {print $5; exit}')
355- if [ -z "$GPU_CORES" ]; then
356- # Fallback: try to parse "Core Count" from Apple GPU section
357- GPU_CORES=$(system_profiler SPDisplaysDataType | awk '/Core Count/ {print $3; exit}')
358- fi
359- echo "GPU Cores: ${GPU_CORES:-Unknown}"
360- else
361- echo "system_profiler not available, cannot determine GPU cores."
362- fi
363- fi
364- echo "::endgroup::"
365-
366- VR_MODE=""
367- if [ "${{ matrix.model.name }}" = "Voxtral-Mini-4B-Realtime-2602" ]; then
368- VR_MODE="vr-offline"
369- fi
370- ${CONDA_RUN} bash .ci/scripts/test_model_e2e.sh metal "${{ matrix.model.repo }}/${{ matrix.model.name }}" "${{ matrix.quant }}" "${RUNNER_ARTIFACT_DIR}" "${VR_MODE}"
310+ # Export and test in the same job so the model never leaves the runner
311+ # (no GitHub Actions artifact upload/download).
312+ MODEL_DIR="$(mktemp -d "${RUNNER_TEMP}/metal_model_XXXXXX")"
313+ ${CONDA_RUN} RUN_EXPORT=1 bash .ci/scripts/test_model_e2e.sh metal "${{ matrix.model.repo }}/${{ matrix.model.name }}" "${{ matrix.quant }}" "${MODEL_DIR}" "${VR_MODE}"
0 commit comments