From 8caad0510dea601eacce1631efe37df7c56a1d70 Mon Sep 17 00:00:00 2001 From: Aoxuan Chen <43376869+chenaoxuan@users.noreply.github.com> Date: Thu, 25 Dec 2025 11:39:38 +0800 Subject: [PATCH] fix e2e rejection-sampler error (#5341) ### What this PR does / why we need it? Fixed the error in the CI process for vllm-ascend/tests/e2e/nightly/ops/triton/test_rejection_sampler.py Error: test_rejection_sampler_block_verify_triton_kernel: duplicate parametrization of 'vocab_size'. - vLLM version: release/v0.13.0 - vLLM main: https://github.com/vllm-project/vllm/commit/bc0a5a0c089844b17cb93f3294348f411e523586 Signed-off-by: chenaoxuan --- tests/e2e/nightly/ops/triton/test_rejection_sampler.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/e2e/nightly/ops/triton/test_rejection_sampler.py b/tests/e2e/nightly/ops/triton/test_rejection_sampler.py index 86992711..3820fd11 100644 --- a/tests/e2e/nightly/ops/triton/test_rejection_sampler.py +++ b/tests/e2e/nightly/ops/triton/test_rejection_sampler.py @@ -61,7 +61,7 @@ IS_GREEDY = torch.zeros(NUM_TOKENS, dtype=torch.bool, device=DEVICE) @pytest.mark.parametrize("bonus_token_ids", [BONUS_TOKEN_IDS]) @pytest.mark.parametrize("uniform_probs", [UNIFORM_PROBS]) @pytest.mark.parametrize("is_greedy", [IS_GREEDY]) -@pytest.mark.parametrize("vocab_size", [BATCH_SIZE]) +@pytest.mark.parametrize("batch_size", [BATCH_SIZE]) @pytest.mark.parametrize("max_spec_len", [MAX_SPEC_LEN]) @pytest.mark.parametrize("vocab_size", [VOCAB_SIZE]) @torch.inference_mode()