chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Migrate performance, accuracy, and quantization tests to CI registry (#17177)

Browse Source 
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
This commit is contained in:
Alison Shao
2026-01-18 23:25:24 -08:00
committed by GitHub
co-authored by Kangyan-Zhou
parent a3d9a21882
commit 8916b9d080
20 changed files with 1050 additions and 1020 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/pr-test-amd.yml
+16 -16
View File
@@ -713,23 +713,23 @@ jobs:
- name: Benchmark single latency
timeout-minutes: 20
run: |
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_small
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_default
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
- name: Benchmark online latency
timeout-minutes: 15
run: |
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_default
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 offline throughput
timeout-minutes: 15
run: |
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default
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 python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size
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]
@@ -768,17 +768,17 @@ jobs:
- name: Benchmark offline throughput (w/o RadixAttention)
timeout-minutes: 15
run: |
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_without_radix_cache
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
- name: Benchmark offline throughput (w/ Triton)
timeout-minutes: 15
run: |
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_with_triton_attention_backend
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 python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
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
performance-test-2-gpu-amd:
needs: [check-changes, stage-a-test-1-amd]
@@ -822,32 +822,32 @@ jobs:
- name: Benchmark single latency (TP=2)
timeout-minutes: 25
run: |
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_tp2_bs1
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 python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_torch_compile_tp2_bs1
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 python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_default
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 python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
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 python3 -m unittest test_bench_serving.TestBenchServing.test_pp_offline_throughput_default_decode
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 python3 -m unittest test_bench_serving.TestBenchServing.test_pp_long_context_prefill
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:
needs: [check-changes, stage-a-test-1-amd]
@@ -886,7 +886,7 @@ jobs:
- name: Evaluate Accuracy
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
bash scripts/ci/amd_ci_exec.sh -w /sglang-checkout/test/registered/eval -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
accuracy-test-2-gpu-amd:
needs: [check-changes, accuracy-test-1-gpu-amd]
@@ -926,7 +926,7 @@ jobs:
- name: Evaluate accuracy (TP=2)
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -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/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
pr-test-amd-finish:
needs: