PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
Enable Torch compilation for throughput tests (#2181)
Xin Hee55beddc5bf5
diff --git a/test/e2e/test_cuda/test_sglang_throughput.py b/test/e2e/test_cuda/test_sglang_throughput.pyindex 5cb291343..dcdaf05a2 100644--- a/test/e2e/test_cuda/test_sglang_throughput.py+++ b/test/e2e/test_cuda/test_sglang_throughput.py@@ -46,6 +46,8 @@ from typing import Listimport pytestimport torch+pytestmark = pytest.mark.enable_torch_compile+# ---------------------------------------------------------------------------# Output sink# ---------------------------------------------------------------------------diff --git a/test/e2e/test_cuda/test_vllm_throughput.py b/test/e2e/test_cuda/test_vllm_throughput.pyindex e2c0006ae..a13a339fe 100644--- a/test/e2e/test_cuda/test_vllm_throughput.py+++ b/test/e2e/test_cuda/test_vllm_throughput.py@@ -55,6 +55,8 @@ from typing import Listimport pytestimport torch+pytestmark = pytest.mark.enable_torch_compile+# ---------------------------------------------------------------------------# Output sink# ---------------------------------------------------------------------------