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 9, 23:00 UTC
[ROCm][CI] Remove DS async eplb accuracy test from AMD CI (#32717)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Micah Williamson committed
Jan 20, 2026 at 15:40 UTC
22375f8d13dbf5c201c6f1564f72310193930816
1 file changed
-11
.buildkite/test-amd.yaml
-11
@@ -1673,17 +1673,6 @@ steps:
1673
commands:
1674
- bash .buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh 0.8 200 8020 2 1
1675
1676
-- label: DeepSeek V2-Lite Async EPLB Accuracy
1677
- timeout_in_minutes: 60
1678
- mirror_hardwares: [amdexperimental]
1679
- agent_pool: mi325_4
1680
- # grade: Blocking
1681
- gpu: h100
1682
- optional: true
1683
- num_gpus: 4
1684
- working_dir: "/vllm-workspace"
1685
- commands:
1686
- - bash .buildkite/scripts/scheduled_integration_test/deepseek_v2_lite_ep_async_eplb.sh 0.25 1319 8030
1676
1677
- label: Qwen3-Next-80B-A3B-Instruct MTP Async EPLB Accuracy
1678
timeout_in_minutes: 60