anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[CI][NPU] Onboard Qwen-Image perf to Ascend A3 nightly (#7970)

Browse Source 
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com>
This commit is contained in:
NumberWanGao Hanwangyu
 authored and GitHub committed 2026-09-24 04:04:53 +00:00
1 parent 67aa30c966
commit db82a55162
2 files changed
+176 -1
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.buildkite/npu/test-npu-nightly.yml
+36
View File
@@ -247,6 +247,42 @@ steps:
buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
exit $$EXIT
- label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image · Single-NPU"
source_file_dependencies: diffusion_qwen_image_perf
key: nightly-diffusion-x2iat-performance-qwen-image-single-npu
timeout_in_minutes: 180
mirror_hardwares: a3_npu_2
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
HF_TOKEN: "${HF_TOKEN}"
DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
commands:
- export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
- |
set +e
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m "npu and A3 and cards_1" --test-config-file tests/dfx/perf/tests/test_qwen_image_vllm_omni.json
EXIT=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
exit $$EXIT
- label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image · 4-NPU"
source_file_dependencies: diffusion_qwen_image_perf
key: nightly-diffusion-x2iat-performance-qwen-image-4npu
timeout_in_minutes: 180
mirror_hardwares: a3_npu_4
env:
VLLM_WORKER_MULTIPROC_METHOD: spawn
HF_TOKEN: "${HF_TOKEN}"
DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
commands:
- export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
- |
set +e
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m "npu and A3 and cards_4" --test-config-file tests/dfx/perf/tests/test_qwen_image_vllm_omni.json
EXIT=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
exit $$EXIT
- group: ":card_index_dividers: Diffusion X2V Model Test"
key: nightly-diffusion-x2v-group
depends_on: upload-nightly-pipeline
tests/dfx/perf/tests/test_qwen_image_vllm_omni.json
+140 -1
View File
@@ -60,6 +60,42 @@
}
]
},
{
"test_name": "test_qwen_image_single_device_a3",
"mark": [
{
"hardware_marks": {
"res": {
"npu": "A3"
},
"num_cards": 1
}
},
"full_model",
"diffusion"
],
"description": "Single-device baseline (no parallelism)",
"server_type": "vllm-omni",
"server_params": {
"model": "Qwen/Qwen-Image",
"serve_args": {
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "512x512_steps20",
"dataset": "random",
"task": "t2i",
"width": 512,
"height": 512,
"num-inference-steps": 20,
"num-prompts": 10,
"max-concurrency": 1,
"enable-negative-prompt": true
}
]
},
{
"test_name": "test_qwen_image_single_device_step_execution",
"mark": [
@@ -144,13 +180,66 @@
}
]
},
{
"test_name": "test_qwen_image_single_device_step_execution_a3",
"mark": [
{
"hardware_marks": {
"res": {
"npu": "A3"
},
"num_cards": 1
}
},
"full_model",
"diffusion"
],
"description": "Single-device step execution: sequential 512 plus 512 concurrency sweep. One server (max-num-seqs 8).",
"server_type": "vllm-omni",
"server_params": {
"model": "Qwen/Qwen-Image",
"serve_args": {
"enable-diffusion-pipeline-profiler": true,
"step-execution": true,
"max-num-seqs": 8
}
},
"benchmark_params": [
{
"name": "512x512_steps20",
"dataset": "random",
"task": "t2i",
"width": 512,
"height": 512,
"num-inference-steps": 20,
"num-prompts": 10,
"max-concurrency": 1,
"enable-negative-prompt": true
},
{
"name": "512x512_steps20_high_concurrency",
"dataset": "random",
"task": "t2i",
"width": 512,
"height": 512,
"num-inference-steps": 20,
"num-prompts": [20, 40, 80, 160],
"max-concurrency": [1, 2, 4, 8],
"warmup-requests": 8,
"warmup-concurrency": 8,
"warmup-num-inference-steps": 20,
"enable-negative-prompt": true
}
]
},
{
"test_name": "test_qwen_image_ulysses2_cfg2_vae_patch4",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": ["H100", "B200"]
"cuda": ["H100", "B200"],
"npu": "A3"
},
"num_cards": 4
}
@@ -265,5 +354,55 @@
}
}
]
},
{
"test_name": "test_qwen_image_ulysses2_cfg2_cache_dit_a3",
"mark": [
{
"hardware_marks": {
"res": {
"npu": "A3"
},
"num_cards": 4
}
},
"full_model",
"diffusion"
],
"description": "Ulysses SP=2 + CFG-parallel=2 + CacheDiT acceleration",
"server_type": "vllm-omni",
"server_params": {
"model": "Qwen/Qwen-Image",
"serve_args": {
"ulysses-degree": 2,
"cfg-parallel-size": 2,
"cache-backend": "cache_dit",
"cache-config": {
"Fn_compute_blocks": 1,
"Bn_compute_blocks": 0,
"max_warmup_steps": 4,
"residual_diff_threshold": 0.24,
"max_continuous_cached_steps": 3,
"enable_taylorseer": false,
"taylorseer_order": 1,
"scm_steps_mask_policy": null,
"scm_steps_policy": "dynamic"
},
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "512x512_steps20",
"dataset": "random",
"task": "t2i",
"width": 512,
"height": 512,
"num-inference-steps": 20,
"num-prompts": 10,
"max-concurrency": 1,
"enable-negative-prompt": true
}
]
}
]