Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Enhance lora tests with more layer and rank variations #3243

Merged
merged 18 commits into from
Mar 10, 2024
Prev Previous commit
remove redundant code
  • Loading branch information
tterrysun committed Mar 9, 2024
commit 00338220c7e98d86bda928137f1e1b4c9c35fd60
4 changes: 0 additions & 4 deletions tests/lora/test_layer_variation.py
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,6 @@
import pytest
from random import sample
import tempfile
import torch
from transformers import AutoModelForCausalLM

import vllm
Expand Down Expand Up @@ -73,9 +72,6 @@ def do_sample(llm,
@pytest.mark.parametrize("target_modules", TARGET_MODULES_LIST)
@pytest.mark.parametrize("rank", [8, 16, 32, 64])
def test_layer_variation_correctness(tp_size, target_modules, rank):
if torch.cuda.device_count() < tp_size:
pytest.skip(f"Not enough GPUs for tensor parallelism {tp_size}")

llm = vllm.LLM(MODEL_PATH,
enable_lora=True,
max_num_seqs=16,
Expand Down
Loading