[Misc] Fix Current vLLM config is not set. warnings, assert to avoid issues in the future (#31747)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Lucas Wilkinson
2026-01-08 15:20:49 -08:00
committed by GitHub
co-authored by Luka Govedič
parent 5d3b6097ad
commit 6cdf015c3c
48 changed files with 380 additions and 240 deletions
+13 -7
View File
@@ -111,7 +111,7 @@ def create_packed_lora(
return LoRAModel(lora_id, 8, loras)
def test_replace_submodules(dist_init, dummy_model):
def test_replace_submodules(default_vllm_config, dist_init, dummy_model):
model = dummy_model
manager = LoRAModelManager(
model,
@@ -133,7 +133,7 @@ def test_replace_submodules(dist_init, dummy_model):
@pytest.mark.parametrize("device", DEVICES)
def test_lora_model_manager(dist_init, dummy_model, device):
def test_lora_model_manager(default_vllm_config, dist_init, dummy_model, device):
model = dummy_model
model_lora1 = create_lora(
1, model, ["layer1.dense1", "dense2", "lm_head"], device=device
@@ -199,7 +199,9 @@ def test_lora_model_manager(dist_init, dummy_model, device):
@pytest.mark.parametrize("device", DEVICES)
def test_lora_lru_cache_model_manager(dist_init, dummy_model, device):
def test_lora_lru_cache_model_manager(
default_vllm_config, dist_init, dummy_model, device
):
model = dummy_model
model_lora1 = create_lora(
1, model, ["layer1.dense1", "dense2", "lm_head"], device=device
@@ -289,7 +291,7 @@ def test_lora_lru_cache_model_manager(dist_init, dummy_model, device):
@pytest.mark.parametrize("device", DEVICES)
def test_lru_lora_model_manager(dist_init, dummy_model, device):
def test_lru_lora_model_manager(default_vllm_config, dist_init, dummy_model, device):
# This tests just the LRU cache functionality, everything else is
# tested in test_lora_model_manager
model = dummy_model
@@ -415,7 +417,9 @@ def test_lru_lora_model_manager(dist_init, dummy_model, device):
@pytest.mark.parametrize("device", DEVICES)
def test_lru_cache_worker_adapter_manager(dist_init, dummy_model, device, tmp_path):
def test_lru_cache_worker_adapter_manager(
default_vllm_config, dist_init, dummy_model, device, tmp_path
):
lora_config = LoRAConfig(
max_lora_rank=8, max_cpu_loras=4, max_loras=4, lora_dtype=DEFAULT_DTYPE
)
@@ -529,7 +533,9 @@ def test_lru_cache_worker_adapter_manager(dist_init, dummy_model, device, tmp_pa
@pytest.mark.parametrize("device", DEVICES)
def test_worker_adapter_manager(dist_init, dummy_model_gate_up, device, tmp_path):
def test_worker_adapter_manager(
default_vllm_config, dist_init, dummy_model_gate_up, device, tmp_path
):
# Should remove every LoRA not specified in the request.
lora_config = LoRAConfig(
max_lora_rank=8, max_cpu_loras=4, max_loras=4, lora_dtype=DEFAULT_DTYPE
@@ -636,7 +642,7 @@ def test_worker_adapter_manager(dist_init, dummy_model_gate_up, device, tmp_path
@pytest.mark.parametrize("device", DEVICES)
def test_packed_loras(dist_init, dummy_model_gate_up, device):
def test_packed_loras(default_vllm_config, dist_init, dummy_model_gate_up, device):
model = dummy_model_gate_up
model_lora = create_packed_lora(
1,