Fix timeout when using LoRA adapters with Nemotron Super (#40916)

Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
This commit is contained in:
danisereb
2026-04-30 01:39:49 +08:00
committed by GitHub
parent 4a42aba380
commit d1a75e303d
2 changed files with 1 additions and 140 deletions
-107
View File
@@ -943,110 +943,3 @@ def test_target_modules_match_packed_runtime_modules(
("layer1.dense2", RowParallelLinearWithLoRA),
],
)
@pytest.mark.parametrize("device", DEVICES)
def test_load_adapter_warns_on_unsupported_modules(
default_vllm_config, dist_init, dummy_model_gate_up, device, tmp_path
):
"""Test that _load_adapter warns when a LoRA adapter contains modules
not in the model's supported LoRA target modules."""
from unittest.mock import patch
import vllm.lora.worker_manager as wm_module
lora_config = LoRAConfig(
max_lora_rank=8, max_cpu_loras=4, max_loras=4, lora_dtype=DEFAULT_DTYPE
)
dummy_lora_files = f"{tmp_path}/lora_adapter"
os.makedirs(dummy_lora_files, exist_ok=True)
create_peft_lora(
dummy_model_gate_up,
save_dir=dummy_lora_files,
target_modules=["layer1.dense1", "dense2"],
lora_dtype=DEFAULT_DTYPE,
)
model_config = ModelConfig(max_model_len=16)
vllm_config = VllmConfig(model_config=model_config, lora_config=lora_config)
vllm_config.scheduler_config.max_num_seqs = 4
vllm_config.scheduler_config.max_num_batched_tokens = 2
worker_manager = WorkerLoRAManager(vllm_config, device, EMBEDDING_MODULES)
worker_manager.vocab_size = dummy_model_gate_up.unpadded_vocab_size
worker_manager.create_lora_manager(dummy_model_gate_up)
# Patch from_local_checkpoint to inject an unsupported module
original_from_checkpoint = LoRAModel.from_local_checkpoint
def patched_from_checkpoint(*args, **kwargs):
lora = original_from_checkpoint(*args, **kwargs)
lora.loras["unsupported_module"] = LoRALayerWeights(
module_name="unsupported_module",
rank=8,
lora_alpha=16,
lora_a=torch.randn(8, 10),
lora_b=torch.randn(10, 8),
)
return lora
lora_request = LoRARequest("test", 1, dummy_lora_files)
with (
patch.object(LoRAModel, "from_local_checkpoint", patched_from_checkpoint),
patch.object(wm_module.logger, "warning_once") as mock_warning,
):
worker_manager._load_adapter(lora_request)
warning_args = mock_warning.call_args_list
found = any("unsupported_module" in str(call) for call in warning_args)
assert found, (
f"Expected warning about 'unsupported_module', got: {warning_args}"
)
@pytest.mark.parametrize("device", DEVICES)
def test_load_adapter_warns_on_target_modules_restriction(
default_vllm_config, dist_init, dummy_model_gate_up, device, tmp_path
):
"""Test that _load_adapter warns when a LoRA adapter contains modules
excluded by the deployment-time target_modules restriction."""
from unittest.mock import patch
import vllm.lora.worker_manager as wm_module
# Restrict to only dense2 — adapter has dense1 which will be excluded
lora_config = LoRAConfig(
max_lora_rank=8,
max_cpu_loras=4,
max_loras=4,
lora_dtype=DEFAULT_DTYPE,
target_modules=["dense2"],
)
dummy_lora_files = f"{tmp_path}/lora_adapter"
os.makedirs(dummy_lora_files, exist_ok=True)
create_peft_lora(
dummy_model_gate_up,
save_dir=dummy_lora_files,
target_modules=["layer1.dense1", "dense2"],
lora_dtype=DEFAULT_DTYPE,
)
model_config = ModelConfig(max_model_len=16)
vllm_config = VllmConfig(model_config=model_config, lora_config=lora_config)
vllm_config.scheduler_config.max_num_seqs = 4
vllm_config.scheduler_config.max_num_batched_tokens = 2
worker_manager = WorkerLoRAManager(vllm_config, device, EMBEDDING_MODULES)
worker_manager.vocab_size = dummy_model_gate_up.unpadded_vocab_size
worker_manager.create_lora_manager(dummy_model_gate_up)
lora_request = LoRARequest("test", 1, dummy_lora_files)
with patch.object(wm_module.logger, "warning_once") as mock_warning:
worker_manager._load_adapter(lora_request)
warning_args = mock_warning.call_args_list
# dense1 is supported by the model but excluded by target_modules
found = any("target_modules" in str(call) for call in warning_args)
assert found, (
f"Expected warning about target_modules restriction, got: {warning_args}"
)