fix: adding performance logging for nightly diffusion (#18023)

.github/workflows/nightly-test-nvidia.yml

@@ -389,6 +389,7 @@ jobs:
         env:
           SGLANG_DIFFUSION_SLACK_TOKEN: ${{ secrets.SGLANG_DIFFUSION_SLACK_TOKEN }}
           GITHUB_RUN_ID: ${{ github.run_id }}
+          GPU_CONFIG: "1-gpu-runner"
 
         timeout-minutes: 60
         run: |
@@ -398,6 +399,24 @@ jobs:
             --partition-id ${{ matrix.part }} \
             --total-partitions 2
 
+      - name: Collect diffusion performance metrics
+        if: always()
+        run: |
+          python3 scripts/ci/save_diffusion_metrics.py \
+            --gpu-config 1-gpu-runner \
+            --run-id ${{ github.run_id }} \
+            --output python/diffusion-metrics-1gpu-partition-${{ matrix.part }}.json \
+            --results-json python/diffusion-results.json
+
+      - name: Upload diffusion metrics
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: diffusion-metrics-1gpu-partition-${{ matrix.part }}
+          path: python/diffusion-metrics-1gpu-partition-${{ matrix.part }}.json
+          retention-days: 90
+          if-no-files-found: ignore
+
 
   nightly-test-multimodal-server-2-gpu:
     if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-multimodal-server-2-gpu')
@@ -422,6 +441,7 @@ jobs:
         env:
           SGLANG_DIFFUSION_SLACK_TOKEN: ${{ secrets.SGLANG_DIFFUSION_SLACK_TOKEN }}
           GITHUB_RUN_ID: ${{ github.run_id }}
+          GPU_CONFIG: "2-gpu-runner"
 
         timeout-minutes: 60
         run: |
@@ -431,6 +451,24 @@ jobs:
             --partition-id ${{ matrix.part }} \
             --total-partitions 2
 
+      - name: Collect diffusion performance metrics
+        if: always()
+        run: |
+          python3 scripts/ci/save_diffusion_metrics.py \
+            --gpu-config 2-gpu-runner \
+            --run-id ${{ github.run_id }} \
+            --output python/diffusion-metrics-2gpu-partition-${{ matrix.part }}.json \
+            --results-json python/diffusion-results.json
+
+      - name: Upload diffusion metrics
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: diffusion-metrics-2gpu-partition-${{ matrix.part }}
+          path: python/diffusion-metrics-2gpu-partition-${{ matrix.part }}.json
+          retention-days: 90
+          if-no-files-found: ignore
+
   # B200 Performance tests - 4 GPU
   nightly-test-perf-4-gpu-b200:
     if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-4-gpu-b200')
@@ -475,12 +513,14 @@ jobs:
           cd test
           python3 run_suite.py --hw cuda --suite nightly-8-gpu-b200 --nightly --continue-on-error --timeout-per-file 2400
 
-  # Consolidate performance metrics from all 8-GPU jobs
+  # Consolidate performance metrics from all jobs
   consolidate-metrics:
     if: github.repository == 'sgl-project/sglang' && always()
     needs:
       - nightly-test-general-8-gpu-h200
       - nightly-test-general-8-gpu-b200
+      - nightly-test-multimodal-server-1-gpu
+      - nightly-test-multimodal-server-2-gpu
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
@@ -491,7 +531,7 @@ jobs:
       - name: Download all partition metrics
         uses: actions/download-artifact@v4
         with:
-          pattern: metrics-*
+          pattern: "*metrics-*"
           path: metrics/
           merge-multiple: true
 

docs/performance_dashboard/app.js

@@ -14,12 +14,17 @@ let currentMetricType = 'throughput'; // throughput, latency, ttft, inputThrough
 
 // Metric type definitions
 const metricTypes = {
-    throughput: { label: 'Overall Throughput', unit: 'tokens/sec', field: 'throughput' },
-    outputThroughput: { label: 'Output Throughput', unit: 'tokens/sec', field: 'outputThroughput' },
-    inputThroughput: { label: 'Input Throughput', unit: 'tokens/sec', field: 'inputThroughput' },
-    latency: { label: 'Latency', unit: 'ms', field: 'latency' },
-    ttft: { label: 'Time to First Token', unit: 'ms', field: 'ttft' },
-    accLength: { label: 'Accept Length', unit: 'tokens', field: 'accLength', filterInvalid: true }
+    // Text/VLM metrics
+    throughput: { label: 'Overall Throughput', unit: 'tokens/sec', field: 'throughput', type: 'text' },
+    outputThroughput: { label: 'Output Throughput', unit: 'tokens/sec', field: 'outputThroughput', type: 'text' },
+    inputThroughput: { label: 'Input Throughput', unit: 'tokens/sec', field: 'inputThroughput', type: 'text' },
+    latency: { label: 'Latency', unit: 'ms', field: 'latency', type: 'text' },
+    ttft: { label: 'Time to First Token', unit: 'ms', field: 'ttft', type: 'text' },
+    accLength: { label: 'Accept Length', unit: 'tokens', field: 'accLength', filterInvalid: true, type: 'text' },
+    // Diffusion metrics
+    e2eMs: { label: 'End-to-End Time', unit: 'ms', field: 'e2e_ms', type: 'diffusion' },
+    avgDenoiseMs: { label: 'Avg Denoise Time', unit: 'ms', field: 'avg_denoise_ms', type: 'diffusion' },
+    medianDenoiseMs: { label: 'Median Denoise Time', unit: 'ms', field: 'median_denoise_ms', type: 'diffusion' }
 };
 
 // Chart.js default configuration for dark theme
@@ -142,32 +147,51 @@ async function fetchMetricsForRun(run) {
     }
 }
 
+// Helper function to detect if result is diffusion type
+function isDiffusionResult(result) {
+    return result.test_type === 'diffusion' || (result.tests && !result.benchmarks);
+}
+
 // Populate filter dropdowns
 function populateFilters() {
     const gpuConfigs = new Set();
     const models = new Set();
+    const testNames = new Set(); // For diffusion tests
     const batchSizes = new Set();
     const ioLengths = new Set();
 
     allMetricsData.forEach(run => {
         run.results.forEach(result => {
             gpuConfigs.add(result.gpu_config);
-            models.add(result.model);
-            // Try new structure first (benchmarks_by_io_len), fall back to flat benchmarks
-            if (result.benchmarks_by_io_len) {
-                Object.entries(result.benchmarks_by_io_len).forEach(([ioKey, ioData]) => {
-                    ioLengths.add(ioKey);
-                    ioData.benchmarks.forEach(bench => {
-                        batchSizes.add(bench.batch_size);
+
+            // Handle diffusion results
+            if (isDiffusionResult(result)) {
+                models.add(result.test_suite || 'diffusion');
+                if (result.tests) {
+                    result.tests.forEach(test => {
+                        testNames.add(test.test_name);
                     });
-                });
-            } else if (result.benchmarks) {
-                result.benchmarks.forEach(bench => {
-                    batchSizes.add(bench.batch_size);
-                    if (bench.input_len && bench.output_len) {
-                        ioLengths.add(`${bench.input_len}_${bench.output_len}`);
-                    }
-                });
+                }
+            }
+            // Handle text/VLM results
+            else {
+                models.add(result.model);
+                // Try new structure first (benchmarks_by_io_len), fall back to flat benchmarks
+                if (result.benchmarks_by_io_len) {
+                    Object.entries(result.benchmarks_by_io_len).forEach(([ioKey, ioData]) => {
+                        ioLengths.add(ioKey);
+                        ioData.benchmarks.forEach(bench => {
+                            batchSizes.add(bench.batch_size);
+                        });
+                    });
+                } else if (result.benchmarks) {
+                    result.benchmarks.forEach(bench => {
+                        batchSizes.add(bench.batch_size);
+                        if (bench.input_len && bench.output_len) {
+                            ioLengths.add(`${bench.input_len}_${bench.output_len}`);
+                        }
+                    });
+                }
             }
         });
     });
@@ -345,7 +369,16 @@ function createMetricTabs() {
     const tabsContainer = document.getElementById('metric-tabs');
     tabsContainer.innerHTML = '';
 
-    Object.entries(metricTypes).forEach(([key, metric], index) => {
+    // Detect if current data is diffusion or text
+    const isDiffusion = detectCurrentDataType() === 'diffusion';
+    const dataType = isDiffusion ? 'diffusion' : 'text';
+
+    // Filter metrics based on data type
+    const relevantMetrics = Object.entries(metricTypes).filter(([key, metric]) =>
+        metric.type === dataType
+    );
+
+    relevantMetrics.forEach(([key, metric], index) => {
         const tab = document.createElement('div');
         tab.className = index === 0 ? 'tab active' : 'tab';
         tab.textContent = metric.label;
@@ -353,6 +386,31 @@ function createMetricTabs() {
         tab.onclick = () => selectMetricTab(key, tab);
         tabsContainer.appendChild(tab);
     });
+
+    // Set initial metric type
+    if (relevantMetrics.length > 0) {
+        currentMetricType = relevantMetrics[0][0];
+    }
+}
+
+function detectCurrentDataType() {
+    // Check if currently selected model/GPU config has diffusion data
+    const gpuFilter = document.getElementById('gpu-filter')?.value;
+    const modelFilter = currentModel;
+
+    if (!gpuFilter || !modelFilter) return 'text';
+
+    for (const run of allMetricsData) {
+        for (const result of run.results) {
+            if (result.gpu_config === gpuFilter) {
+                const resultModel = result.test_suite || result.model;
+                if (resultModel === modelFilter && isDiffusionResult(result)) {
+                    return 'diffusion';
+                }
+            }
+        }
+    }
+    return 'text';
 }
 
 function selectMetricTab(metricKey, tabElement) {
@@ -374,6 +432,8 @@ function handleModelFilterChange(model) {
     updateVariantFilter();
     // Update IO length filter based on new model selection
     updateIoLenFilter();
+    // Recreate metric tabs in case data type changed (text vs diffusion)
+    createMetricTabs();
     updateCharts();
 }
 
@@ -383,6 +443,8 @@ function handleGpuFilterChange() {
     updateVariantFilter();
     // Update IO length filter based on new GPU selection
     updateIoLenFilter();
+    // Recreate metric tabs in case data type changed (text vs diffusion)
+    createMetricTabs();
     updateCharts();
 }
 
@@ -518,6 +580,7 @@ function prepareChartData(gpuFilter, modelFilter, variantFilter, ioLenFilter, ba
 // Prepare chart data grouped by batch size - each batch size is a separate series
 function prepareChartDataByBatch(gpuFilter, modelFilter, variantFilter, ioLenFilter, batchFilter) {
     const batchDataMap = new Map(); // batch_size -> Map of variant -> data
+    const testDataMap = new Map(); // For diffusion: test_name -> data
 
     allMetricsData.forEach(run => {
         const runDate = new Date(run.run_date);
@@ -525,6 +588,37 @@ function prepareChartDataByBatch(gpuFilter, modelFilter, variantFilter, ioLenFil
         run.results.forEach(result => {
             // Apply filters - GPU and Model are required (no "all" option)
             if (result.gpu_config !== gpuFilter) return;
+
+            // Handle diffusion results
+            if (isDiffusionResult(result)) {
+                const resultModel = result.test_suite || 'diffusion';
+                if (resultModel !== modelFilter) return;
+
+                if (result.tests) {
+                    result.tests.forEach(test => {
+                        const testName = test.test_name;
+                        if (!testDataMap.has(testName)) {
+                            testDataMap.set(testName, {
+                                label: testName,
+                                data: [],
+                                model: resultModel,
+                                testName: testName
+                            });
+                        }
+
+                        testDataMap.get(testName).data.push({
+                            x: runDate,
+                            e2e_ms: test.e2e_ms,
+                            avg_denoise_ms: test.avg_denoise_ms,
+                            median_denoise_ms: test.median_denoise_ms,
+                            runId: run.run_id
+                        });
+                    });
+                }
+                return;
+            }
+
+            // Handle text/VLM results
             if (result.model !== modelFilter) return;
             if (variantFilter !== 'all' && result.variant !== variantFilter) return;
 
@@ -622,6 +716,17 @@ function prepareChartDataByBatch(gpuFilter, modelFilter, variantFilter, ioLenFil
 
     // Sort data points by date and convert to array format
     const result = {};
+
+    // For diffusion data, use test names as "batch sizes"
+    if (testDataMap.size > 0) {
+        testDataMap.forEach((series, testName) => {
+            series.data.sort((a, b) => a.x - b.x);
+            result[testName] = [series]; // Each test is its own series
+        });
+        return result;
+    }
+
+    // For text/VLM data, use batch sizes
     batchDataMap.forEach((variantMap, batchSize) => {
         variantMap.forEach(series => {
             series.data.sort((a, b) => a.x - b.x);
@@ -642,7 +747,16 @@ function updateMetricChart(chartDataByBatch, metricType) {
     activeCharts = [];
 
     const metric = metricTypes[metricType];
-    const batchSizes = Object.keys(chartDataByBatch).sort((a, b) => parseInt(a) - parseInt(b));
+    const isDiffusion = metric.type === 'diffusion';
+
+    // For diffusion, keys are test names; for text, keys are batch sizes
+    const keys = Object.keys(chartDataByBatch);
+    if (!isDiffusion) {
+        keys.sort((a, b) => parseInt(a) - parseInt(b));
+    } else {
+        keys.sort(); // Alphabetical sort for test names
+    }
+    const batchSizes = keys; // Keep variable name for compatibility
 
     if (batchSizes.length === 0) {
         container.innerHTML = '<div class="no-data">No data available for the selected filters</div>';
@@ -682,7 +796,8 @@ function updateMetricChart(chartDataByBatch, metricType) {
 
         const title = document.createElement('div');
         title.className = 'batch-chart-title';
-        title.textContent = `Batch Size: ${batchSize}`;
+        // For diffusion, show test name; for text, show batch size
+        title.textContent = isDiffusion ? `Test: ${batchSize}` : `Batch Size: ${batchSize}`;
         chartWrapper.appendChild(title);
 
         const chartContainer = document.createElement('div');

python/sglang/multimodal_gen/test/server/conftest.py

@@ -1,4 +1,97 @@
-_GLOBAL_PERF_RESULTS = []
+import os
+
+import pytest
+
+print("[CONFTEST] Loading conftest.py at import time")
+
+
+def pytest_configure(config):
+    """
+    Create the perf results StashKey once and store it in config.
+    This hook runs once per test session, before module double-import issues.
+    """
+    if not hasattr(config, "_diffusion_perf_key"):
+        config._diffusion_perf_key = pytest.StashKey[list]()
+        print(f"[CONFTEST] Created perf_results_key: {config._diffusion_perf_key}")
+
+
+def add_perf_results(config, results: list):
+    """Add performance results to the shared stash."""
+    # Get the shared key from config (created once in pytest_configure)
+    key = config._diffusion_perf_key
+    existing = config.stash.get(key, [])
+    existing.extend(results)
+    config.stash[key] = existing
+    print(f"[CONFTEST] Added {len(results)} results, total now: {len(existing)}")
+
+
+@pytest.fixture(scope="session")
+def perf_config(request):
+    """Provide access to pytest config for storing perf results."""
+    return request.config
+
+
+def _write_github_step_summary(content: str):
+    """Write content to GitHub Step Summary if available."""
+    summary_file = os.environ.get("GITHUB_STEP_SUMMARY")
+    if summary_file:
+        with open(summary_file, "a") as f:
+            f.write(content)
+
+
+def _write_results_json(results: list, output_path: str = "diffusion-results.json"):
+    """Write performance results to JSON file for CI artifact collection."""
+    import json
+
+    try:
+        with open(output_path, "w") as f:
+            json.dump(results, f, indent=2)
+        print(f"[CONFTEST] Wrote results to {output_path}")
+    except Exception as e:
+        print(f"[CONFTEST] Failed to write results JSON: {e}")
+
+
+def _generate_diffusion_markdown_report(results: list) -> str:
+    """Generate a markdown report for diffusion performance results."""
+    if not results:
+        return ""
+
+    gpu_config = os.environ.get("GPU_CONFIG", "")
+    header = "## Diffusion Performance Summary"
+    if gpu_config:
+        header += f" [{gpu_config}]"
+    header += "\n\n"
+
+    # Main performance table
+    markdown = header
+    markdown += "| Test Suite | Test Name | Modality | E2E (ms) | Avg Denoise (ms) | Median Denoise (ms) |\n"
+    markdown += "| ---------- | --------- | -------- | -------- | ---------------- | ------------------- |\n"
+
+    for entry in sorted(results, key=lambda x: (x["class_name"], x["test_name"])):
+        modality = entry.get("modality", "image")
+        markdown += (
+            f"| {entry['class_name']} | {entry['test_name']} | {modality} | "
+            f"{entry['e2e_ms']:.2f} | {entry['avg_denoise_ms']:.2f} | "
+            f"{entry['median_denoise_ms']:.2f} |\n"
+        )
+
+    # Video-specific metrics table (if any video tests)
+    video_results = [r for r in results if r.get("modality") == "video"]
+    if video_results:
+        markdown += "\n### Video Generation Metrics\n\n"
+        markdown += "| Test Name | FPS | Total Frames | Avg Frame Time (ms) |\n"
+        markdown += "| --------- | --- | ------------ | ------------------- |\n"
+        for entry in video_results:
+            fps = entry.get("frames_per_second", "N/A")
+            frames = entry.get("total_frames", "N/A")
+            avg_frame = entry.get("avg_frame_time_ms", "N/A")
+            if isinstance(fps, float):
+                fps = f"{fps:.2f}"
+            if isinstance(avg_frame, float):
+                avg_frame = f"{avg_frame:.2f}"
+            markdown += f"| {entry['test_name']} | {fps} | {frames} | {avg_frame} |\n"
+
+    return markdown
 
 
 def pytest_sessionfinish(session):
@@ -6,9 +99,15 @@ def pytest_sessionfinish(session):
     This hook is called by pytest at the end of the entire test session.
     It prints a consolidated summary of all performance results.
     """
-    if not _GLOBAL_PERF_RESULTS:
+    # Get results from stash using the shared key from config
+    key = session.config._diffusion_perf_key
+    results = session.config.stash.get(key, [])
+    print(f"\n[DEBUG] pytest_sessionfinish called, has {len(results)} entries")
+    if not results:
+        print("[DEBUG] No results collected, skipping summary output")
         return
 
+    # Print to stdout (existing behavior)
     print("\n\n" + "=" * 35 + " Performance Summary " + "=" * 35)
     print(
         f"{'Test Suite':<30} | {'Test Name':<20} | {'E2E (ms)':>12} | {'Avg Denoise (ms)':>18} | {'Median Denoise (ms)':>20}"
@@ -25,7 +124,7 @@ def pytest_sessionfinish(session):
         + "-" * 20
     )
 
-    for entry in sorted(_GLOBAL_PERF_RESULTS, key=lambda x: x["class_name"]):
+    for entry in sorted(results, key=lambda x: x["class_name"]):
         print(
             f"{entry['class_name']:<30} | {entry['test_name']:<20} | {entry['e2e_ms']:>12.2f} | "
             f"{entry['avg_denoise_ms']:>18.2f} | {entry['median_denoise_ms']:>20.2f}"
@@ -34,7 +133,7 @@ def pytest_sessionfinish(session):
     print("=" * 91)
 
     print("\n\n" + "=" * 36 + " Detailed Reports " + "=" * 37)
-    for entry in sorted(_GLOBAL_PERF_RESULTS, key=lambda x: x["class_name"]):
+    for entry in sorted(results, key=lambda x: x["class_name"]):
         print(f"\n--- Details for {entry['class_name']} / {entry['test_name']} ---")
         stage_report = ", ".join(
             f"{name}:{duration:.2f}ms"
@@ -51,3 +150,11 @@ def pytest_sessionfinish(session):
             )
             print(f"    Sampled Steps: {step_report}")
     print("=" * 91)
+
+    # Write to GitHub Step Summary (new behavior for CI monitoring)
+    markdown_report = _generate_diffusion_markdown_report(results)
+    if markdown_report:
+        _write_github_step_summary(markdown_report)
+
+    # Write results to JSON file for CI artifact collection
+    _write_results_json(results)

python/sglang/multimodal_gen/test/server/test_server_common.py

@@ -18,7 +18,7 @@ from openai import OpenAI
 from sglang.multimodal_gen.runtime.platforms import current_platform
 from sglang.multimodal_gen.runtime.utils.logging_utils import init_logger
 from sglang.multimodal_gen.runtime.utils.perf_logger import RequestPerfRecord
-from sglang.multimodal_gen.test.server.conftest import _GLOBAL_PERF_RESULTS
+from sglang.multimodal_gen.test.server import conftest
 from sglang.multimodal_gen.test.server.test_server_utils import (
     VALIDATOR_REGISTRY,
     PerformanceValidator,
@@ -134,6 +134,7 @@ class DiffusionServerBase:
 
     _perf_results: list[dict[str, Any]] = []
     _improved_baselines: list[dict[str, Any]] = []
+    _pytest_config = None  # Store pytest config for stash access
 
     @classmethod
     def setup_class(cls):
@@ -142,9 +143,21 @@ class DiffusionServerBase:
 
     @classmethod
     def teardown_class(cls):
-        for result in cls._perf_results:
-            result["class_name"] = cls.__name__
-            _GLOBAL_PERF_RESULTS.append(result)
+        print(
+            f"\n[DEBUG teardown_class] Called for {cls.__name__}, _perf_results has {len(cls._perf_results)} entries"
+        )
+        if cls._pytest_config:
+            # Add results to pytest stash (shared across all import contexts)
+            for result in cls._perf_results:
+                result["class_name"] = cls.__name__
+            conftest.add_perf_results(cls._pytest_config, cls._perf_results)
+            print(
+                f"[DEBUG teardown_class] Added {len(cls._perf_results)} results to stash"
+            )
+        else:
+            print(
+                "[DEBUG teardown_class] No pytest_config available, skipping stash update"
+            )
 
         if cls._improved_baselines:
             import json
@@ -160,6 +173,11 @@ Consider updating perf_baselines.json with the snippets below:
                 )
             print(output)
 
+    @pytest.fixture(autouse=True)
+    def _capture_pytest_config(self, request):
+        """Capture pytest config for use in teardown_class."""
+        self.__class__._pytest_config = request.config
+
     def _client(self, ctx: ServerContext) -> OpenAI:
         """Get OpenAI client for the server."""
         return OpenAI(
@@ -261,6 +279,9 @@ Consider updating perf_baselines.json with the snippets below:
             )
 
         self.__class__._perf_results.append(result)
+        print(
+            f"[DEBUG _validate_and_record] Appended result for {case.id}, class {self.__class__.__name__} now has {len(self.__class__._perf_results)} results"
+        )
 
     def _check_for_improvement(
         self,

scripts/ci/merge_metrics.py

@@ -22,8 +22,14 @@ from datetime import datetime, timezone
 
 def find_partition_files(input_dir: str) -> list[str]:
     """Find all partition metric files in the input directory."""
-    pattern = os.path.join(input_dir, "**/metrics-*.json")
-    return glob.glob(pattern, recursive=True)
+    patterns = [
+        os.path.join(input_dir, "**/metrics-*.json"),
+        os.path.join(input_dir, "**/diffusion-metrics-*.json"),
+    ]
+    files = set()
+    for pattern in patterns:
+        files.update(glob.glob(pattern, recursive=True))
+    return list(files)
 
 
 def load_partition_metrics(filepath: str) -> dict | None:

scripts/ci/save_diffusion_metrics.py

@@ -0,0 +1,163 @@
+#!/usr/bin/env python3
+"""Collect and save diffusion performance metrics for artifact collection in CI.
+
+This script reads diffusion test results from the pytest stash and saves them
+with metadata for the performance dashboard.
+
+Usage:
+    python3 scripts/ci/save_diffusion_metrics.py \
+        --gpu-config 1-gpu-runner \
+        --run-id 12345678 \
+        --output test/diffusion-metrics-1gpu.json \
+        --results-json test/diffusion-results.json
+"""
+
+import argparse
+import json
+import os
+import sys
+from datetime import datetime, timezone
+
+
+def load_diffusion_results(results_file: str) -> list[dict]:
+    """Load diffusion performance results from JSON file."""
+    if not os.path.exists(results_file):
+        print(f"Warning: Results file not found: {results_file}")
+        return []
+
+    try:
+        with open(results_file, "r", encoding="utf-8") as f:
+            data = json.load(f)
+        return data if isinstance(data, list) else [data]
+    except (json.JSONDecodeError, OSError) as e:
+        print(f"Warning: Failed to parse {results_file}: {e}")
+        return []
+
+
+def transform_diffusion_result(result: dict, gpu_config: str) -> dict:
+    """Transform a diffusion result to match dashboard expectations.
+
+    Dashboard expects:
+    - Separate test_name, class_name
+    - Numeric metrics in consistent units
+    - Optional modality field
+    """
+    return {
+        "test_name": result.get("test_name"),
+        "class_name": result.get("class_name"),
+        "modality": result.get("modality", "image"),
+        "e2e_ms": result.get("e2e_ms"),
+        "avg_denoise_ms": result.get("avg_denoise_ms"),
+        "median_denoise_ms": result.get("median_denoise_ms"),
+        "stage_metrics": result.get("stage_metrics", {}),
+        "sampled_steps": result.get("sampled_steps", {}),
+        # Video-specific metrics (if present)
+        "frames_per_second": result.get("frames_per_second"),
+        "total_frames": result.get("total_frames"),
+        "avg_frame_time_ms": result.get("avg_frame_time_ms"),
+    }
+
+
+def group_results_by_class(results: list[dict], gpu_config: str) -> list[dict]:
+    """Group diffusion results by test class (suite).
+
+    Returns list with one entry per test class, containing all tests in that class.
+    """
+    groups = {}
+
+    for result in results:
+        class_name = result.get("class_name", "unknown")
+
+        if class_name not in groups:
+            groups[class_name] = {
+                "gpu_config": gpu_config,
+                "test_suite": class_name,
+                "tests": [],
+            }
+
+        transformed = transform_diffusion_result(result, gpu_config)
+        groups[class_name]["tests"].append(transformed)
+
+    return list(groups.values())
+
+
+def save_metrics(
+    gpu_config: str,
+    run_id: str,
+    output_file: str,
+    results_file: str,
+) -> bool:
+    """Collect diffusion metrics and save to output file."""
+    timestamp = datetime.now(timezone.utc).isoformat()
+
+    # Load diffusion results
+    raw_results = load_diffusion_results(results_file)
+    print(f"Loaded {len(raw_results)} diffusion test result(s)")
+
+    # Group by test class
+    grouped = group_results_by_class(raw_results, gpu_config)
+
+    # Create metrics structure
+    metrics = {
+        "run_id": run_id,
+        "timestamp": timestamp,
+        "gpu_config": gpu_config,
+        "test_type": "diffusion",
+        "results": grouped,
+    }
+
+    # Ensure output directory exists and write output
+    try:
+        os.makedirs(os.path.dirname(output_file) or ".", exist_ok=True)
+        with open(output_file, "w", encoding="utf-8") as f:
+            json.dump(metrics, f, indent=2)
+
+        if not raw_results:
+            print(f"Created empty metrics file: {output_file}")
+        else:
+            print(f"Saved diffusion metrics to: {output_file}")
+        return True
+    except OSError as e:
+        print(f"Error writing metrics file: {e}")
+        return False
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Collect diffusion performance metrics from test results"
+    )
+    parser.add_argument(
+        "--gpu-config",
+        required=True,
+        help="GPU configuration (e.g., 1-gpu-runner, 2-gpu-runner)",
+    )
+    parser.add_argument(
+        "--run-id",
+        required=True,
+        help="GitHub Actions run ID",
+    )
+    parser.add_argument(
+        "--output",
+        required=True,
+        help="Output file path for metrics JSON",
+    )
+    parser.add_argument(
+        "--results-json",
+        required=True,
+        help="Path to diffusion results JSON file",
+    )
+
+    args = parser.parse_args()
+
+    success = save_metrics(
+        gpu_config=args.gpu_config,
+        run_id=args.run_id,
+        output_file=args.output,
+        results_file=args.results_json,
+    )
+
+    sys.exit(0 if success else 1)
+
+
+if __name__ == "__main__":
+    main()