A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 02:15 UTC
[CI Bugfix] Skip failing Tensorizer+LoRA test (#20724)
Michael Goin committed
Jul 10, 2025 at 21:15 UTC
be1e128dfb5b50c586eae1d4ee4d6f24f6076dd8
1 file changed
+4
tests/lora/test_llama_tp.py
+4
@@ -4,6 +4,8 @@ import subprocess
4
import sys
5
from typing import Union
6
7
+import pytest
8
+
9
import vllm
10
from vllm import LLM
11
from vllm.lora.request import LoRARequest
@@ -149,6 +151,8 @@ def test_llama_lora_tp4_fully_sharded_loras(sql_lora_files):
151
generate_and_test(llm, sql_lora_files)
152
153
154
+@pytest.mark.skip(reason=("Skipping this test as tensorizer is not "
155
+ "working with LoRA as of #19619"))
156
@multi_gpu_test(num_gpus=2)
157
@create_new_process_for_each_test()
158
def test_tp2_serialize_and_deserialize_lora(tmp_path, sql_lora_files,