From 15dc96e71f9ca0499fc1289424d43a0e12f0700a Mon Sep 17 00:00:00 2001 From: Amit Zuker <203509407+amitz-nv@users.noreply.github.com> Date: Sun, 5 Oct 2025 08:05:57 +0000 Subject: [PATCH] Re-enable test_bielik_11b_v2_2_instruct_multi_lora, fix its API use with pytorch flow LoRA Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com> --- tests/unittest/llmapi/test_llm_pytorch.py | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/tests/unittest/llmapi/test_llm_pytorch.py b/tests/unittest/llmapi/test_llm_pytorch.py index b40c7d8e1881..6ea3508859ba 100644 --- a/tests/unittest/llmapi/test_llm_pytorch.py +++ b/tests/unittest/llmapi/test_llm_pytorch.py @@ -564,7 +564,6 @@ def test_codellama_fp8_with_bf16_lora() -> None: @skip_gpu_memory_less_than_80gb -@pytest.mark.skip(reason="https://nvbugs/5521949") def test_bielik_11b_v2_2_instruct_multi_lora() -> None: model_dir = f"{llm_models_root()}/Bielik-11B-v2.2-Instruct" @@ -591,12 +590,16 @@ def test_bielik_11b_v2_2_instruct_multi_lora() -> None: lora_model.save_pretrained(lora_path) lora_paths.append(lora_path) - trtllm_lora_config = LoraConfig(lora_dir=lora_paths, - lora_target_modules=target_modules, + trtllm_lora_config = LoraConfig(lora_target_modules=target_modules, max_lora_rank=8, max_loras=2, max_cpu_loras=2) - llm = LLM(model_dir, lora_config=trtllm_lora_config) + llm = LLM( + model_dir, + lora_config=trtllm_lora_config, + # Disable CUDA graph + # TODO: remove this once we have a proper fix for CUDA graph in LoRA + cuda_graph_config=None) prompts = [ "Kim był Mikołaj Kopernik i z czego zasłynął?",