From e9a44ea6075122a0d475a9d819ef05558cd581c7 Mon Sep 17 00:00:00 2001 From: YC Tseng Date: Tue, 20 Jan 2026 05:04:15 +0800 Subject: [PATCH] [AMD] fix perf ci errors (#17363) --- .github/workflows/pr-test-amd.yml | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/.github/workflows/pr-test-amd.yml b/.github/workflows/pr-test-amd.yml index 4bd313cc2..b4032c274 100644 --- a/.github/workflows/pr-test-amd.yml +++ b/.github/workflows/pr-test-amd.yml @@ -688,8 +688,8 @@ jobs: - name: Benchmark online latency (LoRA) timeout-minutes: 10 run: | - bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_lora_online_latency - bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_lora_online_latency_with_concurrent_adapter_updates + bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_lora_online_latency + bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_lora_online_latency_with_concurrent_adapter_updates - name: Benchmark offline throughput timeout-minutes: 15 @@ -753,12 +753,12 @@ jobs: - name: Benchmark VLM offline throughput timeout-minutes: 10 run: | - bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_vlm_offline_throughput + bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part2.TestBenchServing1GPUPart2.test_vlm_offline_throughput - name: Benchmark VLM online latency timeout-minutes: 10 run: | - bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_vlm_online_latency + bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part2.TestBenchServing1GPUPart2.test_vlm_online_latency performance-test-1-gpu-part-3-amd: needs: [check-changes, stage-a-test-1-amd] @@ -797,22 +797,22 @@ jobs: - name: Benchmark Scores online latency and throughput timeout-minutes: 10 run: | - bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_score_api_latency_throughput + bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part2.TestBenchServing1GPUPart2.test_score_api_latency_throughput - name: Benchmark Scores online latency and throughput (batch size scaling) timeout-minutes: 10 run: | - bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_score_api_batch_scaling + bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part2.TestBenchServing1GPUPart2.test_score_api_batch_scaling - name: Benchmark Embeddings online latency and throughput timeout-minutes: 10 run: | - bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_embeddings_api_latency_throughput + bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part2.TestBenchServing1GPUPart2.test_embeddings_api_latency_throughput - name: Benchmark Embeddings online latency and throughput (batch size scaling) timeout-minutes: 10 run: | - bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_embeddings_api_batch_scaling + bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part2.TestBenchServing1GPUPart2.test_embeddings_api_batch_scaling performance-test-2-gpu-amd: needs: [check-changes, stage-a-test-1-amd]