[Refactor] Relocate entrypoint tests to match serving code structure (#37593)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
This commit is contained in:
@@ -337,12 +337,16 @@ apply_rocm_test_overrides() {
|
|||||||
--ignore=entrypoints/openai/completion/test_shutdown.py \
|
--ignore=entrypoints/openai/completion/test_shutdown.py \
|
||||||
--ignore=entrypoints/openai/test_completion.py \
|
--ignore=entrypoints/openai/test_completion.py \
|
||||||
--ignore=entrypoints/openai/models/test_models.py \
|
--ignore=entrypoints/openai/models/test_models.py \
|
||||||
--ignore=entrypoints/openai/test_lora_adapters.py \
|
|
||||||
--ignore=entrypoints/openai/test_return_tokens_as_ids.py \
|
--ignore=entrypoints/openai/test_return_tokens_as_ids.py \
|
||||||
--ignore=entrypoints/openai/chat_completion/test_root_path.py \
|
--ignore=entrypoints/openai/chat_completion/test_root_path.py \
|
||||||
--ignore=entrypoints/openai/completion/test_prompt_validation.py "}
|
--ignore=entrypoints/openai/completion/test_prompt_validation.py "}
|
||||||
fi
|
fi
|
||||||
|
|
||||||
|
if [[ $cmds == *" entrypoints/serve"* ]]; then
|
||||||
|
cmds="${cmds} \
|
||||||
|
--ignore=entrypoints/serve/lora/test_lora_adapters.py"
|
||||||
|
fi
|
||||||
|
|
||||||
if [[ $cmds == *" entrypoints/llm "* ]]; then
|
if [[ $cmds == *" entrypoints/llm "* ]]; then
|
||||||
cmds=${cmds//" entrypoints/llm "/" entrypoints/llm \
|
cmds=${cmds//" entrypoints/llm "/" entrypoints/llm \
|
||||||
--ignore=entrypoints/llm/test_chat.py \
|
--ignore=entrypoints/llm/test_chat.py \
|
||||||
|
|||||||
+1
-2
@@ -8,12 +8,11 @@ import pytest
|
|||||||
import pytest_asyncio
|
import pytest_asyncio
|
||||||
from transformers import AutoTokenizer
|
from transformers import AutoTokenizer
|
||||||
|
|
||||||
|
from tests.utils import RemoteOpenAIServer
|
||||||
from vllm.config import ModelConfig
|
from vllm.config import ModelConfig
|
||||||
from vllm.config.utils import getattr_iter
|
from vllm.config.utils import getattr_iter
|
||||||
from vllm.v1.engine.detokenizer import check_stop_strings
|
from vllm.v1.engine.detokenizer import check_stop_strings
|
||||||
|
|
||||||
from ...utils import RemoteOpenAIServer
|
|
||||||
|
|
||||||
MODEL_NAME = "Qwen/Qwen3-0.6B"
|
MODEL_NAME = "Qwen/Qwen3-0.6B"
|
||||||
GEN_ENDPOINT = "/inference/v1/generate"
|
GEN_ENDPOINT = "/inference/v1/generate"
|
||||||
|
|
||||||
+1
-1
@@ -10,7 +10,7 @@ import openai # use the official client for correctness check
|
|||||||
import pytest
|
import pytest
|
||||||
import pytest_asyncio
|
import pytest_asyncio
|
||||||
|
|
||||||
from ...utils import RemoteOpenAIServer
|
from tests.utils import RemoteOpenAIServer
|
||||||
|
|
||||||
# any model with a chat template should work here
|
# any model with a chat template should work here
|
||||||
MODEL_NAME = "Qwen/Qwen3-0.6B"
|
MODEL_NAME = "Qwen/Qwen3-0.6B"
|
||||||
+1
-1
@@ -6,7 +6,7 @@ import httpx
|
|||||||
import pytest
|
import pytest
|
||||||
import pytest_asyncio
|
import pytest_asyncio
|
||||||
|
|
||||||
from ...utils import RemoteLaunchRenderServer
|
from tests.utils import RemoteLaunchRenderServer
|
||||||
|
|
||||||
MODEL_NAME = "hmellor/tiny-random-LlamaForCausalLM"
|
MODEL_NAME = "hmellor/tiny-random-LlamaForCausalLM"
|
||||||
|
|
||||||
Reference in New Issue
Block a user