xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-17 06:15:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix LoRA test (#18123)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li 2025-05-14 18:25:47 +08:00 committed by GitHub
parent 612c2edb4f
commit 259127f8b8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
tests/lora/test_worker.py
View File

@ -58,13 +58,19 @@ def test_worker_apply_lora(sql_lora_files):
download_dir=None, download_dir=None,
load_format="dummy", load_format="dummy",
), ),
parallel_config=ParallelConfig(1, 1, False), parallel_config=ParallelConfig(
pipeline_parallel_size=1,
tensor_parallel_size=1,
data_parallel_size=1,
),
scheduler_config=SchedulerConfig("generate", 32, 32, 32), scheduler_config=SchedulerConfig("generate", 32, 32, 32),
device_config=DeviceConfig("cuda"), device_config=DeviceConfig("cuda"),
cache_config=CacheConfig(block_size=16, cache_config=CacheConfig(
gpu_memory_utilization=1., block_size=16,
swap_space=0, gpu_memory_utilization=1.0,
cache_dtype="auto"), swap_space=0,
cache_dtype="auto",
),
lora_config=LoRAConfig(max_lora_rank=8, max_cpu_loras=32, lora_config=LoRAConfig(max_lora_rank=8, max_cpu_loras=32,
max_loras=32), max_loras=32),
) )