[AMD] CI - migrate perf test and fix stage-b-test-1-gpu-amd (#17340)
Co-authored-by: Bingxu Chen <bingxche@amd.com> Co-authored-by: bingxche <Bingxu.Chen@amd.com> Co-authored-by: michaelzhang-ai <michaelzhang.ai@users.noreply.github.com>
This commit is contained in:
YC Tseng
191
.github/workflows/pr-test-amd.yml
vendored
191
.github/workflows/pr-test-amd.yml
vendored
@@ -639,12 +639,12 @@ jobs:
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 3600
|
||||
|
||||
performance-test-1-gpu-part-1-amd:
|
||||
needs: [check-changes, stage-a-test-1-amd]
|
||||
stage-b-test-small-1-gpu-performance-amd:
|
||||
needs: [check-changes, call-gate, stage-a-test-1-amd]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'performance-test-1-gpu-part-1-amd') ||
|
||||
(inputs.target_stage == 'stage-b-test-small-1-gpu-performance-amd') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
(!failure() && !cancelled()) &&
|
||||
@@ -673,39 +673,17 @@ jobs:
|
||||
- name: Install dependencies
|
||||
run: bash scripts/ci/amd_ci_install_dependency.sh
|
||||
|
||||
- name: Benchmark single latency
|
||||
timeout-minutes: 20
|
||||
- name: Run test
|
||||
timeout-minutes: 30
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_one_batch_1gpu.TestBenchOneBatch1GPU.test_bs1_small
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_one_batch_1gpu.TestBenchOneBatch1GPU.test_bs1_default
|
||||
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-performance-amd --timeout-per-file 1200
|
||||
|
||||
- name: Benchmark online latency
|
||||
timeout-minutes: 15
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_online_latency_default
|
||||
|
||||
- name: Benchmark online latency (LoRA)
|
||||
timeout-minutes: 10
|
||||
run: |
|
||||
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
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_offline_throughput_default
|
||||
|
||||
- name: Benchmark offline throughput (Non-streaming, small batch size)
|
||||
timeout-minutes: 15
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_offline_throughput_non_stream_small_batch_size
|
||||
|
||||
performance-test-1-gpu-part-2-amd:
|
||||
needs: [check-changes, stage-a-test-1-amd]
|
||||
stage-b-test-large-1-gpu-performance-amd:
|
||||
needs: [check-changes, call-gate, stage-a-test-1-amd]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'performance-test-1-gpu-part-2-amd') ||
|
||||
(inputs.target_stage == 'stage-b-test-large-1-gpu-performance-amd') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
(!failure() && !cancelled()) &&
|
||||
@@ -716,6 +694,7 @@ jobs:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
runner: [linux-mi325-gpu-1]
|
||||
part: [0, 1]
|
||||
runs-on: ${{matrix.runner}}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
@@ -734,91 +713,17 @@ jobs:
|
||||
- name: Install dependencies
|
||||
run: bash scripts/ci/amd_ci_install_dependency.sh
|
||||
|
||||
- name: Benchmark offline throughput (w/o RadixAttention)
|
||||
timeout-minutes: 15
|
||||
- name: Run test
|
||||
timeout-minutes: 30
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_offline_throughput_without_radix_cache
|
||||
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-1-gpu-performance-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1200
|
||||
|
||||
- name: Benchmark offline throughput (w/ Triton)
|
||||
timeout-minutes: 15
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_part1.TestBenchServing1GPUPart1.test_offline_throughput_with_triton_attention_backend
|
||||
|
||||
- name: Benchmark offline throughput (w/ FP8)
|
||||
timeout-minutes: 15
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_1gpu_large.TestBenchServing1GPULarge.test_offline_throughput_default_fp8
|
||||
|
||||
- name: Benchmark VLM offline throughput
|
||||
timeout-minutes: 10
|
||||
run: |
|
||||
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 -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]
|
||||
stage-b-test-large-2-gpu-performance-amd:
|
||||
needs: [check-changes, call-gate, stage-a-test-1-amd]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'performance-test-1-gpu-part-3-amd') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
(!failure() && !cancelled()) &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
)
|
||||
)
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
runner: [linux-mi325-gpu-1]
|
||||
runs-on: ${{matrix.runner}}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
|
||||
|
||||
- name: Ensure VRAM is clear
|
||||
run: bash scripts/ensure_vram_clear.sh rocm
|
||||
|
||||
- name: Start CI container
|
||||
run: bash scripts/ci/amd_ci_start_container.sh
|
||||
env:
|
||||
GITHUB_WORKSPACE: ${{ github.workspace }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: bash scripts/ci/amd_ci_install_dependency.sh
|
||||
|
||||
- name: Benchmark Scores online latency and throughput
|
||||
timeout-minutes: 10
|
||||
run: |
|
||||
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 -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 -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 -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]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'performance-test-2-gpu-amd') ||
|
||||
(inputs.target_stage == 'stage-b-test-large-2-gpu-performance-amd') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
(!failure() && !cancelled()) &&
|
||||
@@ -847,47 +752,17 @@ jobs:
|
||||
- name: Install dependencies
|
||||
run: bash scripts/ci/amd_ci_install_dependency.sh
|
||||
|
||||
- name: Benchmark dummy grok (TP=2)
|
||||
- name: Run test
|
||||
timeout-minutes: 30
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh python3 models/test_dummy_grok_models.py
|
||||
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-performance-amd --timeout-per-file 1200
|
||||
|
||||
- name: Benchmark single latency (TP=2)
|
||||
timeout-minutes: 25
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_one_batch_2gpu.TestBenchOneBatch2GPU.test_moe_tp2_bs1
|
||||
|
||||
- name: Benchmark single latency + torch.compile (TP=2)
|
||||
timeout-minutes: 25
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_one_batch_2gpu.TestBenchOneBatch2GPU.test_torch_compile_tp2_bs1
|
||||
|
||||
- name: Benchmark offline throughput (TP=2)
|
||||
timeout-minutes: 25
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_2gpu.TestBenchServing2GPU.test_moe_offline_throughput_default
|
||||
|
||||
- name: Benchmark offline throughput (w/o RadixAttention) (TP=2)
|
||||
timeout-minutes: 25
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_2gpu.TestBenchServing2GPU.test_moe_offline_throughput_without_radix_cache
|
||||
|
||||
- name: Benchmark offline PP decode throughput (PP=2)
|
||||
timeout-minutes: 10
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_2gpu.TestBenchServing2GPU.test_pp_offline_throughput_default_decode
|
||||
|
||||
- name: Benchmark offline PP prefill throughput (PP=2)
|
||||
timeout-minutes: 10
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/perf python3 -m unittest test_bench_serving_2gpu.TestBenchServing2GPU.test_pp_long_context_prefill
|
||||
|
||||
accuracy-test-1-gpu-amd:
|
||||
stage-b-test-small-1-gpu-accuracy-amd:
|
||||
needs: [check-changes, stage-a-test-1-amd]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'accuracy-test-1-gpu-amd') ||
|
||||
(inputs.target_stage == 'stage-b-test-small-1-gpu-accuracy-amd') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
(!failure() && !cancelled()) &&
|
||||
@@ -916,18 +791,17 @@ jobs:
|
||||
- name: Install dependencies
|
||||
run: bash scripts/ci/amd_ci_install_dependency.sh
|
||||
|
||||
- name: Evaluate Accuracy
|
||||
- name: Run test
|
||||
timeout-minutes: 30
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/eval -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
|
||||
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" -e SGLANG_USE_AITER=0 python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-accuracy-amd --timeout-per-file 1800
|
||||
|
||||
accuracy-test-2-gpu-amd:
|
||||
needs: [check-changes, accuracy-test-1-gpu-amd]
|
||||
# Temporarily disabled - uncomment when ready to re-enable (tracked here: https://github.com/sgl-project/sglang/issues/13107)
|
||||
stage-b-test-large-2-gpu-accuracy-amd:
|
||||
needs: [check-changes, stage-a-test-1-amd]
|
||||
if: |
|
||||
always() &&
|
||||
(
|
||||
(inputs.target_stage == 'accuracy-test-2-gpu-amd') ||
|
||||
(inputs.target_stage == 'stage-b-test-large-2-gpu-accuracy-amd') ||
|
||||
(
|
||||
!inputs.target_stage &&
|
||||
(!failure() && !cancelled()) &&
|
||||
@@ -956,10 +830,10 @@ jobs:
|
||||
- name: Install dependencies
|
||||
run: bash scripts/ci/amd_ci_install_dependency.sh
|
||||
|
||||
- name: Evaluate accuracy (TP=2)
|
||||
- name: Run test
|
||||
timeout-minutes: 30
|
||||
run: |
|
||||
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/eval -e SGLANG_USE_AITER_AR=0 -e SGLANG_USE_AITER=0 -e HF_HUB_ENABLE_HF_TRANSFER=0 python3 test_moe_eval_accuracy_large.py
|
||||
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" -e SGLANG_USE_AITER_AR=0 -e SGLANG_USE_AITER=0 -e HF_HUB_ENABLE_HF_TRANSFER=0 python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-accuracy-amd --timeout-per-file 1800
|
||||
|
||||
pr-test-amd-finish:
|
||||
needs:
|
||||
@@ -975,14 +849,13 @@ jobs:
|
||||
stage-b-test-small-1-gpu-amd,
|
||||
stage-b-test-small-1-gpu-amd-mi35x,
|
||||
stage-b-test-large-2-gpu-amd,
|
||||
stage-b-test-small-1-gpu-performance-amd,
|
||||
stage-b-test-large-1-gpu-performance-amd,
|
||||
stage-b-test-large-2-gpu-performance-amd,
|
||||
stage-b-test-small-1-gpu-accuracy-amd,
|
||||
stage-b-test-large-2-gpu-accuracy-amd,
|
||||
stage-c-test-large-8-gpu-amd,
|
||||
stage-c-test-large-8-gpu-amd-mi35x,
|
||||
performance-test-1-gpu-part-1-amd,
|
||||
performance-test-1-gpu-part-2-amd,
|
||||
performance-test-1-gpu-part-3-amd,
|
||||
performance-test-2-gpu-amd,
|
||||
accuracy-test-1-gpu-amd,
|
||||
accuracy-test-2-gpu-amd,
|
||||
]
|
||||
if: always()
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
Reference in New Issue
Block a user