[diffusion] multi-platform: support diffusion on amd and fix encoder loading on MI325 (#13760)
Co-authored-by: Sabre Shao <sabre.shao@amd.com> Co-authored-by: Yusheng (Ethan) Su <yushengsu.thu@gmail.com> Co-authored-by: Hubert Lu <Hubert.Lu@amd.com> Co-authored-by: xsun <sunxiao04@gmail.com>
This commit is contained in:
Yuzhen Zhou
246
.github/workflows/pr-test-amd.yml
vendored
246
.github/workflows/pr-test-amd.yml
vendored
@@ -5,7 +5,6 @@ on:
|
||||
branches: [ main ]
|
||||
paths:
|
||||
- "python/**"
|
||||
- "!python/sglang/multimodal_gen/**"
|
||||
- "scripts/ci/**"
|
||||
- "test/**"
|
||||
- "sgl-kernel/**"
|
||||
@@ -14,7 +13,6 @@ on:
|
||||
branches: [ main ]
|
||||
paths:
|
||||
- "python/**"
|
||||
- "!python/sglang/multimodal_gen/**"
|
||||
- "scripts/ci/**"
|
||||
- "test/**"
|
||||
- "sgl-kernel/**"
|
||||
@@ -41,6 +39,7 @@ jobs:
|
||||
outputs:
|
||||
main_package: ${{ steps.filter.outputs.main_package }}
|
||||
sgl_kernel: ${{ steps.filter.outputs.sgl_kernel }}
|
||||
multimodal_gen: ${{ steps.filter.outputs.multimodal_gen }}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
@@ -56,6 +55,11 @@ jobs:
|
||||
- ".github/workflows/pr-test-amd.yml"
|
||||
sgl_kernel:
|
||||
- "sgl-kernel/**"
|
||||
multimodal_gen:
|
||||
- "python/sglang/multimodal_gen/**"
|
||||
- "python/sglang/cli/**"
|
||||
- "python/*.toml"
|
||||
- ".github/workflows/pr-test-amd.yml"
|
||||
|
||||
# =============================================== sgl-kernel ====================================================
|
||||
sgl-kernel-unit-test-amd:
|
||||
@@ -140,6 +144,242 @@ jobs:
|
||||
run: |
|
||||
docker exec -w /sglang-checkout/test ci_sglang python3 run_suite.py --hw amd --suite stage-a-test-1
|
||||
|
||||
multimodal-gen-test-1-gpu-amd:
|
||||
needs: [check-changes]
|
||||
if: needs.check-changes.outputs.multimodal_gen == 'true'
|
||||
strategy:
|
||||
fail-fast: false
|
||||
max-parallel: 1 # Run one at a time to avoid eviction from resource exhaustion during AITER kernel JIT
|
||||
matrix:
|
||||
runner: [linux-mi325-gpu-1]
|
||||
part: [0, 1] # 2 partitions: 11 tests ÷ 2 = ~5-6 tests each
|
||||
runs-on: ${{matrix.runner}}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Ensure VRAM is clear
|
||||
run: bash scripts/ensure_vram_clear.sh rocm
|
||||
|
||||
- name: Download artifacts
|
||||
if: needs.check-changes.outputs.sgl_kernel == 'true'
|
||||
uses: actions/download-artifact@v4
|
||||
with:
|
||||
path: sgl-kernel/dist/
|
||||
merge-multiple: true
|
||||
pattern: wheel-python3.10-cuda12.9
|
||||
|
||||
- name: Start CI container
|
||||
run: bash scripts/ci/amd_ci_start_container.sh
|
||||
env:
|
||||
GITHUB_WORKSPACE: ${{ github.workspace }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_install_dependency.sh diffusion
|
||||
|
||||
- name: Setup kernel caches
|
||||
run: |
|
||||
# Use the persistent /sgl-data directory (mounted from /home/runner/sgl-data)
|
||||
# This directory persists across container restarts on the self-hosted runner
|
||||
docker exec ci_sglang mkdir -p /sgl-data/aiter-kernels /sgl-data/miopen-cache /sgl-data/hf-cache/hub
|
||||
|
||||
# Clear pre-built AITER kernels from Docker image to avoid segfaults
|
||||
# The image may have stale/incompatible kernels at /sgl-workspace/aiter/aiter/jit/
|
||||
echo "Clearing pre-built AITER kernels from Docker image..."
|
||||
docker exec ci_sglang rm -rf /sgl-workspace/aiter/aiter/jit/*.so 2>/dev/null || true
|
||||
docker exec ci_sglang rm -rf /sgl-data/aiter-kernels/*.so 2>/dev/null || true
|
||||
echo "AITER kernels cleared - will be rebuilt on first use"
|
||||
|
||||
# Create persistent cache marker if /sgl-data is a real mount (not ephemeral)
|
||||
# This tells the test cleanup code to NOT delete downloaded models
|
||||
if docker exec ci_sglang test -d /sgl-data && docker exec ci_sglang mountpoint -q /sgl-data 2>/dev/null; then
|
||||
docker exec ci_sglang touch /sgl-data/hf-cache/.persistent_cache
|
||||
echo "Created .persistent_cache marker - HF cache will persist"
|
||||
else
|
||||
echo "WARNING: /sgl-data is not a mount point - models will be cleaned up after each test"
|
||||
fi
|
||||
|
||||
# Check MIOpen cache (VAE convolution kernels)
|
||||
miopen_files=$(docker exec ci_sglang find /sgl-data/miopen-cache -name "*.udb" 2>/dev/null | wc -l || echo "0")
|
||||
echo "Found ${miopen_files} MIOpen cache files"
|
||||
|
||||
- name: Diagnose HF cache and system resources
|
||||
run: |
|
||||
echo "=== System Memory Status ==="
|
||||
free -h
|
||||
echo ""
|
||||
echo "=== Disk Space ==="
|
||||
df -h /home/runner/sgl-data 2>/dev/null || df -h
|
||||
echo ""
|
||||
echo "=== HF Cache Directory Structure ==="
|
||||
docker exec ci_sglang ls -la /sgl-data/hf-cache/ 2>/dev/null || echo "HF cache dir not found"
|
||||
docker exec ci_sglang ls -la /sgl-data/hf-cache/hub/ 2>/dev/null || echo "HF hub cache not found"
|
||||
echo ""
|
||||
echo "=== Checking for cached diffusion models (1-GPU tests) ==="
|
||||
# Models used in 1-GPU tests: Wan2.1-T2V-1.3B, HunyuanVideo, Qwen-Image, FLUX.1, FLUX.2
|
||||
for model in "Wan-AI--Wan2.1-T2V-1.3B-Diffusers" "tencent--HunyuanVideo" "Qwen--Qwen-Image" "black-forest-labs--FLUX.1-dev" "black-forest-labs--FLUX.2-dev"; do
|
||||
cache_path="/sgl-data/hf-cache/hub/models--${model}"
|
||||
if docker exec ci_sglang test -d "$cache_path"; then
|
||||
size=$(docker exec ci_sglang du -sh "$cache_path" 2>/dev/null | cut -f1)
|
||||
echo "✓ CACHED: $model ($size)"
|
||||
else
|
||||
echo "✗ NOT CACHED: $model"
|
||||
fi
|
||||
done
|
||||
echo ""
|
||||
echo "=== GPU Memory Status ==="
|
||||
docker exec ci_sglang rocm-smi --showmeminfo vram 2>/dev/null || echo "rocm-smi not available"
|
||||
|
||||
- name: Run diffusion server tests (1-GPU)
|
||||
timeout-minutes: 45
|
||||
run: |
|
||||
# AMD CI: All 1-GPU tests except FLUX.2 (FLUX.1 covers same code path)
|
||||
# Tests: T2V, T2I, I2V, LoRA
|
||||
#
|
||||
# HF download env vars:
|
||||
# - HF_HUB_ENABLE_HF_TRANSFER=1: Use faster hf_transfer for downloads (if available)
|
||||
# - HF_HUB_DISABLE_SYMLINKS_WARNING=1: Suppress symlink warnings
|
||||
docker exec \
|
||||
-e SGLANG_E2E_TOLERANCE=0.3 \
|
||||
-e SGLANG_STAGE_TIME_TOLERANCE=0.2 \
|
||||
-e SGLANG_NON_DENOISE_STAGE_TIME_TOLERANCE=0.6 \
|
||||
-e SGLANG_DENOISE_STEP_TOLERANCE=0.6 \
|
||||
-e SGLANG_DENOISE_AGG_TOLERANCE=0.3 \
|
||||
-e SGLANG_TEST_NUM_INFERENCE_STEPS=5 \
|
||||
-e SGLANG_DIFFUSION_ATTENTION_BACKEND=AITER \
|
||||
-e AITER_JIT_DIR=/sgl-data/aiter-kernels \
|
||||
-e MIOPEN_USER_DB_PATH=/sgl-data/miopen-cache \
|
||||
-e HF_HUB_ENABLE_HF_TRANSFER=1 \
|
||||
-e HF_HUB_DISABLE_SYMLINKS_WARNING=1 \
|
||||
-w /sglang-checkout/python \
|
||||
ci_sglang python3 sglang/multimodal_gen/test/run_suite.py \
|
||||
--suite 1-gpu \
|
||||
--partition-id ${{ matrix.part }} \
|
||||
--total-partitions 2 \
|
||||
-k "not flux_2"
|
||||
|
||||
# Post-test diagnostics
|
||||
echo "=== Post-test System Memory Status ==="
|
||||
free -h
|
||||
|
||||
multimodal-gen-test-2-gpu-amd:
|
||||
needs: [check-changes]
|
||||
if: needs.check-changes.outputs.multimodal_gen == 'true'
|
||||
strategy:
|
||||
fail-fast: false
|
||||
max-parallel: 1 # Run one at a time to avoid eviction from resource exhaustion during AITER kernel JIT
|
||||
matrix:
|
||||
runner: [linux-mi325-gpu-2]
|
||||
part: [0, 1] # 2 partitions: 9 tests ÷ 2 = ~4-5 tests each
|
||||
runs-on: ${{matrix.runner}}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Ensure VRAM is clear
|
||||
run: bash scripts/ensure_vram_clear.sh rocm
|
||||
|
||||
- name: Download artifacts
|
||||
if: needs.check-changes.outputs.sgl_kernel == 'true'
|
||||
uses: actions/download-artifact@v4
|
||||
with:
|
||||
path: sgl-kernel/dist/
|
||||
merge-multiple: true
|
||||
pattern: wheel-python3.10-cuda12.9
|
||||
|
||||
- name: Start CI container
|
||||
run: bash scripts/ci/amd_ci_start_container.sh
|
||||
env:
|
||||
GITHUB_WORKSPACE: ${{ github.workspace }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_install_dependency.sh diffusion
|
||||
|
||||
- name: Setup kernel caches
|
||||
run: |
|
||||
# Use the persistent /sgl-data directory (mounted from /home/runner/sgl-data)
|
||||
docker exec ci_sglang mkdir -p /sgl-data/aiter-kernels /sgl-data/miopen-cache /sgl-data/hf-cache/hub
|
||||
|
||||
# Clear pre-built AITER kernels from Docker image to avoid segfaults
|
||||
# The image may have stale/incompatible kernels at /sgl-workspace/aiter/aiter/jit/
|
||||
echo "Clearing pre-built AITER kernels from Docker image..."
|
||||
docker exec ci_sglang rm -rf /sgl-workspace/aiter/aiter/jit/*.so 2>/dev/null || true
|
||||
docker exec ci_sglang rm -rf /sgl-data/aiter-kernels/*.so 2>/dev/null || true
|
||||
echo "AITER kernels cleared - will be rebuilt on first use"
|
||||
|
||||
# Create persistent cache marker if /sgl-data is a real mount (not ephemeral)
|
||||
# This tells the test cleanup code to NOT delete downloaded models
|
||||
if docker exec ci_sglang test -d /sgl-data && docker exec ci_sglang mountpoint -q /sgl-data 2>/dev/null; then
|
||||
docker exec ci_sglang touch /sgl-data/hf-cache/.persistent_cache
|
||||
echo "Created .persistent_cache marker - HF cache will persist"
|
||||
else
|
||||
echo "WARNING: /sgl-data is not a mount point - models will be cleaned up after each test"
|
||||
fi
|
||||
|
||||
# Check MIOpen cache (VAE convolution kernels)
|
||||
miopen_files=$(docker exec ci_sglang find /sgl-data/miopen-cache -name "*.udb" 2>/dev/null | wc -l || echo "0")
|
||||
echo "Found ${miopen_files} MIOpen cache files"
|
||||
|
||||
- name: Diagnose HF cache and system resources
|
||||
run: |
|
||||
echo "=== System Memory Status ==="
|
||||
free -h
|
||||
echo ""
|
||||
echo "=== Disk Space ==="
|
||||
df -h /home/runner/sgl-data 2>/dev/null || df -h
|
||||
echo ""
|
||||
echo "=== HF Cache Directory Structure ==="
|
||||
docker exec ci_sglang ls -la /sgl-data/hf-cache/ 2>/dev/null || echo "HF cache dir not found"
|
||||
docker exec ci_sglang ls -la /sgl-data/hf-cache/hub/ 2>/dev/null || echo "HF hub cache not found"
|
||||
echo ""
|
||||
echo "=== Checking for cached diffusion models (2-GPU tests) ==="
|
||||
# Models used in 2-GPU tests: Wan2.2-T2V-A14B, Wan2.1-T2V-14B, Qwen-Image, FLUX.1
|
||||
for model in "Wan-AI--Wan2.2-T2V-A14B-Diffusers" "Wan-AI--Wan2.1-T2V-14B-Diffusers" "Qwen--Qwen-Image" "black-forest-labs--FLUX.1-dev"; do
|
||||
cache_path="/sgl-data/hf-cache/hub/models--${model}"
|
||||
if docker exec ci_sglang test -d "$cache_path"; then
|
||||
size=$(docker exec ci_sglang du -sh "$cache_path" 2>/dev/null | cut -f1)
|
||||
echo "✓ CACHED: $model ($size)"
|
||||
else
|
||||
echo "✗ NOT CACHED: $model"
|
||||
fi
|
||||
done
|
||||
echo ""
|
||||
echo "=== GPU Memory Status ==="
|
||||
docker exec ci_sglang rocm-smi --showmeminfo vram 2>/dev/null || echo "rocm-smi not available"
|
||||
|
||||
- name: Run diffusion server tests (2-GPU)
|
||||
timeout-minutes: 80
|
||||
run: |
|
||||
# AMD CI: All 2-GPU tests including LoRA
|
||||
# Tests: T2V, T2I, I2V, LoRA
|
||||
#
|
||||
# HF download env vars:
|
||||
# - HF_HUB_ENABLE_HF_TRANSFER=1: Use faster hf_transfer for downloads (if available)
|
||||
# - HF_HUB_DISABLE_SYMLINKS_WARNING=1: Suppress symlink warnings
|
||||
docker exec \
|
||||
-e SGLANG_E2E_TOLERANCE=0.3 \
|
||||
-e SGLANG_STAGE_TIME_TOLERANCE=0.2 \
|
||||
-e SGLANG_NON_DENOISE_STAGE_TIME_TOLERANCE=0.6 \
|
||||
-e SGLANG_DENOISE_STEP_TOLERANCE=0.6 \
|
||||
-e SGLANG_DENOISE_AGG_TOLERANCE=0.3 \
|
||||
-e SGLANG_TEST_NUM_INFERENCE_STEPS=5 \
|
||||
-e SGLANG_DIFFUSION_ATTENTION_BACKEND=AITER \
|
||||
-e AITER_JIT_DIR=/sgl-data/aiter-kernels \
|
||||
-e MIOPEN_USER_DB_PATH=/sgl-data/miopen-cache \
|
||||
-e HF_HUB_ENABLE_HF_TRANSFER=1 \
|
||||
-e HF_HUB_DISABLE_SYMLINKS_WARNING=1 \
|
||||
-w /sglang-checkout/python \
|
||||
ci_sglang python3 sglang/multimodal_gen/test/run_suite.py \
|
||||
--suite 2-gpu \
|
||||
--partition-id ${{ matrix.part }} \
|
||||
--total-partitions 2
|
||||
|
||||
# Post-test diagnostics
|
||||
echo "=== Post-test System Memory Status ==="
|
||||
free -h
|
||||
|
||||
unit-test-backend-1-gpu-amd:
|
||||
needs: [check-changes, stage-a-test-1-amd]
|
||||
if: |
|
||||
@@ -506,6 +746,8 @@ jobs:
|
||||
check-changes,
|
||||
|
||||
sgl-kernel-unit-test-amd,
|
||||
multimodal-gen-test-1-gpu-amd,
|
||||
multimodal-gen-test-2-gpu-amd,
|
||||
|
||||
stage-a-test-1-amd,
|
||||
unit-test-backend-1-gpu-amd,
|
||||
|
||||
Reference in New Issue
Block a user