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

[HunyuanImage][Perf] adapt to deploy config changes (#3996)

Browse Source 
Signed-off-by: dengyunyang <584797741@qq.com>
This commit is contained in:
dengyunyang authored and GitHub committed 2026-05-30 14:48:50 +08:00
1 parent a3456752c5
commit 3b317285c4
4 files changed
+28 -88
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.buildkite/test-nightly.yml
-54
View File
@@ -1033,60 +1033,6 @@ steps:
path: /mnt/hf-cache
type: DirectoryOrCreate
- label: ":full_moon: Diffusion X2I(&A&T) · HunyuanImage3 · DiT Perf Test"
key: nightly-hunyuan-image3-performance
soft_fail: true
timeout_in_minutes: 120
if: build.env("RUN_HUNYUAN_IMAGE3_PERF") == "1"
commands:
- export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
- export DIFFUSION_ATTENTION_BACKEND=FLASH_ATTN
- export CACHE_DIT_VERSION=1.3.0
- |
set +e
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_hunyuan_image_tp4_fp8.json
EXIT1=$$?
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_hunyuan_image_tp2_fp8_sp2.json
EXIT2=$$?
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_hunyuan_image_tp2_fp8_cfgp2.json
EXIT3=$$?
buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
exit $$((EXIT1 | EXIT2 | EXIT3))
agents:
queue: "mithril-h100-pool"
plugins:
- kubernetes:
podSpec:
containers:
- image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 4
volumeMounts:
- name: devshm
mountPath: /dev/shm
- name: hf-cache
mountPath: /root/.cache/huggingface
env:
- name: HF_HOME
value: /root/.cache/huggingface
- name: HF_TOKEN
valueFrom:
secretKeyRef:
name: hf-token-secret
key: token
nodeSelector:
node.kubernetes.io/instance-type: gpu-h100-sxm
volumes:
- name: devshm
emptyDir:
medium: Memory
- name: hf-cache
hostPath:
path: /mnt/hf-cache
type: DirectoryOrCreate
# Diffusion x2v only (Wan, HunyuanVideo, …). x2i/x2a/x2t live in the X2I group above, not here.
- group: ":card_index_dividers: Diffusion X2V Model Test"
key: nightly-diffusion-x2v-group
tests/dfx/perf/tests/test_hunyuan_image_tp2_fp8_cfgp2.json → tests/dfx/perf/tests/test_hunyuan_image_tp2_cfgp2.json
+9 -11
View File
@@ -1,35 +1,33 @@
[
{
"test_name": "test_hunyuan_image_tp2_fp8_cfgp2",
"description": "TP=2 Quantization=fp8 CfgP=2 baseline",
"test_name": "test_hunyuan_image_tp2_cfgp2",
"description": "TP=2 CfgP=2 baseline",
"server_type": "vllm-omni",
"server_params": {
"model": "tencent/HunyuanImage-3.0-Instruct",
"serve_args": {
"deploy_config": "../vllm_omni/deploy/hunyuan_image3_dit.yaml",
"tensor-parallel-size": 2,
"cfg-parallel-size": 2,
"quantization": "fp8",
"distributed-executor-backend": "mp",
"enforce-eager": true,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1024x1024_steps50",
"name": "1024x1024_steps8",
"dataset": "random",
"task": "t2i",
"width": 1024,
"height": 1024,
"num-inference-steps": 50,
"num-inference-steps": 8,
"num-prompts": 10,
"max-concurrency": 1,
"skip-performance-assertion": true,
"baseline": {
"throughput_qps": 0.1035,
"latency_p99": 9.9057,
"peak_memory_mb_max": 66470,
"peak_memory_mb_mean": 66470
"throughput_qps": 0.21,
"latency_p99": 4.7469,
"peak_memory_mb_max": 101100,
"peak_memory_mb_mean": 101100
}
}
]
tests/dfx/perf/tests/test_hunyuan_image_tp2_fp8_sp2.json → tests/dfx/perf/tests/test_hunyuan_image_tp2_sp2.json
+10 -12
View File
@@ -1,35 +1,33 @@
[
{
"test_name": "test_hunyuan_image_tp2_fp8_sp2",
"description": "TP=2 Quantization=fp8 SP=2 baseline",
"test_name": "test_hunyuan_image_tp2_sp2",
"description": "TP=2 SP=2 baseline",
"server_type": "vllm-omni",
"server_params": {
"model": "tencent/HunyuanImage-3.0-Instruct",
"serve_args": {
"deploy-config": "../vllm_omni/deploy/hunyuan_image3_dit.yaml",
"tensor-parallel-size": 2,
"usp": 2,
"quantization": "fp8",
"distributed-executor-backend": "mp",
"enforce-eager": true,
"ulysses-degree": 2,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1024x1024_steps50",
"name": "1024x1024_steps8",
"dataset": "random",
"task": "t2i",
"width": 1024,
"height": 1024,
"num-inference-steps": 50,
"num-inference-steps": 8,
"num-prompts": 10,
"max-concurrency": 1,
"skip-performance-assertion": true,
"baseline": {
"throughput_qps": 0.08,
"latency_p99": 12.0731,
"peak_memory_mb_max": 66314,
"peak_memory_mb_mean": 66314
"throughput_qps": 0.20,
"latency_p99": 5.1025,
"peak_memory_mb_max": 97402,
"peak_memory_mb_mean": 97402
}
}
]
tests/dfx/perf/tests/test_hunyuan_image_tp4_fp8.json → tests/dfx/perf/tests/test_hunyuan_image_tp4.json
+9 -11
View File
@@ -1,34 +1,32 @@
[
{
"test_name": "test_hunyuan_image_tp4_fp8",
"description": "TP=4 Quantization=fp8 baseline",
"test_name": "test_hunyuan_image_tp4",
"description": "TP=4 baseline",
"server_type": "vllm-omni",
"server_params": {
"model": "tencent/HunyuanImage-3.0-Instruct",
"serve_args": {
"deploy-config": "../vllm_omni/deploy/hunyuan_image3_dit.yaml",
"tensor-parallel-size": 4,
"quantization": "fp8",
"distributed-executor-backend": "mp",
"enforce-eager": true,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1024x1024_steps50",
"name": "1024x1024_steps8",
"dataset": "random",
"task": "t2i",
"width": 1024,
"height": 1024,
"num-inference-steps": 50,
"num-inference-steps": 8,
"num-prompts": 10,
"max-concurrency": 1,
"skip-performance-assertion": true,
"baseline": {
"throughput_qps": 0.08,
"latency_p99": 13.1227,
"peak_memory_mb_max": 46838,
"peak_memory_mb_mean": 46838
"throughput_qps": 0.21,
"latency_p99": 4.9235,
"peak_memory_mb_max": 57576,
"peak_memory_mb_mean": 57576
}
}
]