Commit ccaeb6c0 authored by 王敏's avatar 王敏
Browse files

[fix]还原部分代码

parent 5c77fabd
......@@ -190,7 +190,7 @@ def test_mtp_e2e_greedy_correctness_cuda_graph(vllm_runner, common_llm_kwargs,
@pytest.mark.parametrize(
"common_llm_kwargs",
[{
"block_size": 16,
"block_size": 8,
# 2 for small prompt, 256//8 for generated.
"num_gpu_blocks_override": 2 + 256 // 8,
"max_model_len": (2 + 256 // 8) * 8,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment