This commit is contained in:
@@ -8,7 +8,7 @@ import torch
|
||||
from safetensors.torch import load_file
|
||||
from torch import nn
|
||||
|
||||
from vllm.config import ModelConfig, RendererConfig, VllmConfig
|
||||
from vllm.config import ModelConfig, VllmConfig
|
||||
from vllm.config.lora import LoRAConfig
|
||||
from vllm.lora.layers import (
|
||||
ColumnParallelLinearWithLoRA,
|
||||
@@ -422,11 +422,7 @@ def test_lru_cache_worker_adapter_manager(dist_init, dummy_model, device, tmp_pa
|
||||
)
|
||||
|
||||
model_config = ModelConfig(max_model_len=16)
|
||||
vllm_config = VllmConfig(
|
||||
model_config=model_config,
|
||||
renderer_config=RendererConfig(model_config=model_config),
|
||||
lora_config=lora_config,
|
||||
)
|
||||
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
|
||||
@@ -529,11 +525,7 @@ def test_worker_adapter_manager(dist_init, dummy_model_gate_up, device, tmp_path
|
||||
)
|
||||
|
||||
model_config = ModelConfig(max_model_len=16)
|
||||
vllm_config = VllmConfig(
|
||||
model_config=model_config,
|
||||
renderer_config=RendererConfig(model_config=model_config),
|
||||
lora_config=lora_config,
|
||||
)
|
||||
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
|
||||
|
||||
@@ -11,7 +11,6 @@ from vllm.config import (
|
||||
DeviceConfig,
|
||||
ModelConfig,
|
||||
ParallelConfig,
|
||||
RendererConfig,
|
||||
SchedulerConfig,
|
||||
VllmConfig,
|
||||
)
|
||||
@@ -44,7 +43,6 @@ def test_worker_apply_lora(qwen3_lora_files):
|
||||
|
||||
vllm_config = VllmConfig(
|
||||
model_config=model_config,
|
||||
renderer_config=RendererConfig(model_config=model_config),
|
||||
load_config=LoadConfig(
|
||||
download_dir=None,
|
||||
load_format="dummy",
|
||||
|
||||
Reference in New Issue
Block a user