[V1] LoRA - Enable more V1 tests (#14315)

Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
This commit is contained in:
Varun Sundar Rabindranath
2025-03-06 11:55:42 +08:00
committed by GitHub
co-authored by Varun Sundar Rabindranath
parent f5f7f00cd9
commit 3dbd2d813a
5 changed files with 57 additions and 8 deletions
-3
View File
@@ -55,7 +55,6 @@ def v1(run_with_both_engines_lora):
pass
@pytest.mark.skip_v1
@fork_new_process_for_each_test
def test_chatglm3_lora(chatglm3_lora_files):
llm = vllm.LLM(MODEL_PATH,
@@ -75,7 +74,6 @@ def test_chatglm3_lora(chatglm3_lora_files):
assert output2[i] == EXPECTED_LORA_OUTPUT[i]
@pytest.mark.skip_v1
@multi_gpu_test(num_gpus=4)
@fork_new_process_for_each_test
def test_chatglm3_lora_tp4(chatglm3_lora_files):
@@ -97,7 +95,6 @@ def test_chatglm3_lora_tp4(chatglm3_lora_files):
assert output2[i] == EXPECTED_LORA_OUTPUT[i]
@pytest.mark.skip_v1
@multi_gpu_test(num_gpus=4)
@fork_new_process_for_each_test
def test_chatglm3_lora_tp4_fully_sharded_loras(chatglm3_lora_files):