iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[XPU][CI] add heterogeneous TP UT (#49651)

Browse Source 
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
This commit is contained in:
liuzhenwei
2026-07-26 02:01:15 +00:00
committed by GitHub
parent 7a6a5b3667
commit b153ae6089
1 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/intel_jobs/misc_intel.yaml
+7 -4
View File
@@ -125,13 +125,13 @@ steps:
pytest -v -s v1/kv_offload &&
pytest -v -s v1/kv_connector/unit/test_offloading_connector.py'
- label: NixlConnector PD accuracy (2 GPUs)
- label: NixlConnector PD accuracy (4 GPUs)
timeout_in_minutes: 60
num_devices: 2
num_devices: 4
device: intel_gpu
agent_tags:
label: production
gpu: 2+
gpu: 4+
mem: 16+
no_plugin: true
working_dir: "."
@@ -148,7 +148,10 @@ steps:
- >-
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
'cd tests &&
bash v1/kv_connector/nixl_integration/run_xpu_disagg_accuracy_test.sh'
bash v1/kv_connector/nixl_integration/run_xpu_disagg_accuracy_test.sh &&
PREFILLER_TP_SIZE=2 DECODER_TP_SIZE=1 bash v1/kv_connector/nixl_integration/run_xpu_disagg_accuracy_test.sh &&
PREFILLER_TP_SIZE=1 DECODER_TP_SIZE=2 bash v1/kv_connector/nixl_integration/run_xpu_disagg_accuracy_test.sh &&
PREFILLER_TP_SIZE=2 DECODER_TP_SIZE=2 bash v1/kv_connector/nixl_integration/run_xpu_disagg_accuracy_test.sh'
- label: Regression
key: regression