From 2d339ddef1a4e16480307f9e50d9dd56dc030af6 Mon Sep 17 00:00:00 2001 From: pllimax Date: Tue, 8 Sep 2026 21:14:48 +0800 Subject: [PATCH] [NPU] Phase A calibration: full GSM8K eval for dp_attention mixed-chunk (#38422) --- .github/workflows/_npu-pr-test-stage.yml | 3 +++ .../npu/basic_function/dp_attn/test_npu_dp_attention.py | 4 +++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/.github/workflows/_npu-pr-test-stage.yml b/.github/workflows/_npu-pr-test-stage.yml index 2171550d4..42cd4b0e4 100644 --- a/.github/workflows/_npu-pr-test-stage.yml +++ b/.github/workflows/_npu-pr-test-stage.yml @@ -255,6 +255,9 @@ jobs: install_pkg "${pkg}" done + # Install sgl-eval (CLI used by run_eval.py's `sgl-eval run ...`) if missing. + command -v sgl-eval >/dev/null 2>&1 || install_pkg "sgl-eval==0.1.0" + cd test # Append `--nightly` and `--continue-on-error` when the job belongs to the nightly pipeline. # --nightly: Collect test cases registered for nightly runs. diff --git a/test/registered/npu/basic_function/dp_attn/test_npu_dp_attention.py b/test/registered/npu/basic_function/dp_attn/test_npu_dp_attention.py index a830ea2b6..dc3489181 100644 --- a/test/registered/npu/basic_function/dp_attn/test_npu_dp_attention.py +++ b/test/registered/npu/basic_function/dp_attn/test_npu_dp_attention.py @@ -24,7 +24,7 @@ from sglang.test.test_utils import ( ) register_npu_ci(est_time=400, suite="base-b-test-4-npu-a3") -register_npu_ci(est_time=400, suite="nightly-4-npu-a3", nightly=True) +register_npu_ci(est_time=2400, suite="nightly-4-npu-a3", nightly=True) class TestDPAttentionDP2TP2( @@ -74,6 +74,8 @@ class TestDPAttentionMixedChunk( CustomTestCase, NPUGSM8KMixin, ): + # Use full GSM8K dataset to avoid sampling variance. + gsm8k_num_examples = 1319 gsm8k_accuracy_thres = 0.34 @classmethod