[CI/Build] Fix LoRA test (#19350)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

tests/lora/conftest.py

@@ -164,11 +164,6 @@ def mixtral_lora_files():
     return snapshot_download(repo_id="SangBinCho/mixtral-lora")
 
 
-@pytest.fixture(scope="session")
-def gemma_lora_files():
-    return snapshot_download(repo_id="wskwon/gemma-7b-test-lora")
-
-
 @pytest.fixture(scope="session")
 def chatglm3_lora_files():
     return snapshot_download(repo_id="jeeejeee/chatglm3-text2sql-spider")

tests/lora/test_llama_tp.py

@@ -4,9 +4,6 @@ import subprocess
 import sys
 from typing import Union
 
-import pytest
-import ray
-
 import vllm
 from vllm import LLM
 from vllm.lora.request import LoRARequest
@@ -121,37 +118,6 @@ def test_llama_lora(sql_lora_files):
     generate_and_test(llm, sql_lora_files)
 
 
-# Skipping for v1 as v1 doesn't have a good way to expose the num_gpu_blocks
-# used by the engine yet.
-@pytest.mark.skip_v1
-@create_new_process_for_each_test()
-def test_llama_lora_warmup(sql_lora_files):
-    """Test that the LLM initialization works with a warmup LORA path and
-    is more conservative"""
-
-    @ray.remote(num_gpus=1)
-    def get_num_gpu_blocks_lora():
-        llm = vllm.LLM(MODEL_PATH, enable_lora=True, max_num_seqs=16)
-        num_gpu_blocks_lora_warmup = llm.llm_engine.cache_config.num_gpu_blocks
-        return num_gpu_blocks_lora_warmup
-
-    @ray.remote(num_gpus=1)
-    def get_num_gpu_blocks_no_lora():
-        llm = vllm.LLM(MODEL_PATH, max_num_seqs=16)
-        num_gpu_blocks_no_lora_warmup = (
-            llm.llm_engine.cache_config.num_gpu_blocks)
-        return num_gpu_blocks_no_lora_warmup
-
-    num_gpu_blocks_lora_warmup = ray.get(get_num_gpu_blocks_lora.remote())
-    num_gpu_blocks_no_lora_warmup = ray.get(
-        get_num_gpu_blocks_no_lora.remote())
-    assert num_gpu_blocks_lora_warmup < num_gpu_blocks_no_lora_warmup, (
-        "The warmup with lora should be more "
-        "conservative than without lora, therefore the number of "
-        "memory blocks for the KV cache should be "
-        "less when using lora than when not using lora")
-
-
 @multi_gpu_test(num_gpus=4)
 @create_new_process_for_each_test()
 def test_llama_lora_tp4(sql_lora_files):

tests/lora/test_lora_functions.py

@@ -15,13 +15,6 @@ MODEL_PATH = "meta-llama/Llama-2-7b-hf"
 LORA_MODULE_PATH = "yard1/llama-2-7b-sql-lora-test"
 LORA_RANK = 8
 
-# @pytest.fixture(autouse=True)
-# def v1(run_with_both_engines_lora):
-#     # Simple autouse wrapper to run both engines for each test
-#     # This can be promoted up to conftest.py to run for every
-#     # test in a package
-#     pass
-
 
 def make_lora_request(lora_id: int):
     return LoRARequest(lora_name=f"{lora_id}",

tests/lora/test_phi.py

@@ -11,14 +11,6 @@ MODEL_PATH = "microsoft/phi-2"
 PROMPT_TEMPLATE = "### Instruct: {sql_prompt}\n\n### Context: {context}\n\n### Output:"  # noqa: E501
 
 
-@pytest.fixture(autouse=True)
-def v1(run_with_both_engines_lora):
-    # Simple autouse wrapper to run both engines for each test
-    # This can be promoted up to conftest.py to run for every
-    # test in a package
-    pass
-
-
 def do_sample(llm: vllm.LLM, lora_path: str, lora_id: int) -> list[str]:
     prompts = [
         PROMPT_TEMPLATE.format(
@@ -59,7 +51,7 @@ def do_sample(llm: vllm.LLM, lora_path: str, lora_id: int) -> list[str]:
 
 # Skipping for V1 for now as we are hitting,
 # "Head size 80 is not supported by FlashAttention." error.
-@pytest.mark.skip_v1
+@pytest.mark.skip(reason="Head size 80 is not supported by FlashAttention")
 def test_phi2_lora(phi2_lora_files):
     # We enable enforce_eager=True here to reduce VRAM usage for lora-test CI,
     # Otherwise, the lora-test will fail due to CUDA OOM.

tests/lora/test_worker.py

@@ -16,6 +16,8 @@ from vllm.lora.request import LoRARequest
 from vllm.v1.worker.gpu_worker import Worker as V1Worker
 from vllm.worker.worker import Worker
 
+NUM_LORAS = 16
+
 
 @patch.dict(os.environ, {"RANK": "0"})
 def test_worker_apply_lora(sql_lora_files):
@@ -58,12 +60,12 @@ def test_worker_apply_lora(sql_lora_files):
         device_config=DeviceConfig("cuda"),
         cache_config=CacheConfig(
             block_size=16,
-            gpu_memory_utilization=1.0,
             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_loras=32),
+                               max_cpu_loras=NUM_LORAS,
+                               max_loras=NUM_LORAS),
     )
     worker = worker_cls(
         vllm_config=vllm_config,
@@ -78,9 +80,9 @@ def test_worker_apply_lora(sql_lora_files):
     set_active_loras(worker, [])
     assert worker.list_loras() == set()
 
-    n_loras = 32
     lora_requests = [
-        LoRARequest(str(i + 1), i + 1, sql_lora_files) for i in range(n_loras)
+        LoRARequest(str(i + 1), i + 1, sql_lora_files)
+        for i in range(NUM_LORAS)
     ]
 
     set_active_loras(worker, lora_requests)
@@ -89,12 +91,12 @@ def test_worker_apply_lora(sql_lora_files):
         for lora_request in lora_requests
     }
 
-    for i in range(32):
+    for i in range(NUM_LORAS):
         random.seed(i)
         iter_lora_requests = random.choices(lora_requests,
-                                            k=random.randint(1, n_loras))
+                                            k=random.randint(1, NUM_LORAS))
         random.shuffle(iter_lora_requests)
-        iter_lora_requests = iter_lora_requests[:-random.randint(0, n_loras)]
+        iter_lora_requests = iter_lora_requests[:-random.randint(0, NUM_LORAS)]
         set_active_loras(worker, lora_requests)
         assert worker.list_loras().issuperset(
             {lora_request.lora_int_id