A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 11, 13:45 UTC
[ci] Mark PrimeRL integration test as soft fail (#30578)
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Kevin H. Luu committed
Dec 12, 2025 at 14:13 UTC
b4039c08b5dd0a14d5c1ccac8557aa11732d857c
1 file changed
+2
-1
.buildkite/test-pipeline.yaml
+2
-1
@@ -1346,6 +1346,7 @@ steps:
1346
- label: Prime-RL Integration Test # 15min
1347
timeout_in_minutes: 30
1348
optional: true
1349
+ soft_fail: true
1350
num_gpus: 2
1351
working_dir: "/vllm-workspace"
1352
source_file_dependencies:
@@ -1379,4 +1380,4 @@ steps:
1380
num_gpus: 2
1381
working_dir: "/vllm-workspace"
1382
commands:
1382
- - bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh 0.8 200 8020 2 1
\ No newline at end of file
1383
+ - bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh 0.8 200 8020 2 1