EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[CI/UT] Unify model usage via ModelScope in CI (#1207)

Browse Source 
### What this PR does / why we need it?
Unify Model Usage via ModelScope

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?
CI passed

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
zhangxinyuehfad
2025-07-04 10:52:17 +08:00
committed by GitHub
parent a5f33590d3
commit 4e910186de
9 changed files with 17 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/conftest.py
View File

@@ -25,7 +25,7 @@ from typing import Any, List, Optional, Tuple, TypeVar, Union
import numpy as np
import pytest
import torch
from huggingface_hub import snapshot_download
from modelscope import snapshot_download # type: ignore[import-untyped]
from PIL import Image
from torch import nn
from transformers import (AutoConfig, AutoModelForCausalLM, AutoTokenizer,
@@ -387,7 +387,7 @@ def example_prompts() -> list[str]:
@pytest.fixture(scope="session")
def ilama_lora_files():
return snapshot_download(repo_id="jeeejeee/ilama-text2sql-spider")
return snapshot_download(repo_id="vllm-ascend/ilama-text2sql-spider")
class HfRunner:

3
tests/e2e/multicard/test_ilama_lora_tp2.py
View File

@@ -1,4 +1,5 @@
import pytest
from modelscope import snapshot_download # type: ignore
from tests.conftest import VllmRunner
from tests.e2e.singlecard.test_ilama_lora import (EXPECTED_LORA_OUTPUT,
@@ -7,7 +8,7 @@ from tests.e2e.singlecard.test_ilama_lora import (EXPECTED_LORA_OUTPUT,
@pytest.mark.parametrize("distributed_executor_backend", ["mp"])
def test_ilama_lora_tp2(distributed_executor_backend, ilama_lora_files):
with VllmRunner(model_name=MODEL_PATH,
with VllmRunner(snapshot_download(MODEL_PATH),
enable_lora=True,
max_loras=4,
max_model_len=1024,

5
tests/e2e/singlecard/test_ilama_lora.py
View File

@@ -1,10 +1,11 @@
# SPDX-License-Identifier: Apache-2.0
import vllm
from modelscope import snapshot_download # type: ignore
from vllm.lora.request import LoRARequest
from tests.conftest import VllmRunner
MODEL_PATH = "ArthurZ/ilama-3.2-1B"
MODEL_PATH = "vllm-ascend/ilama-3.2-1B"
PROMPT_TEMPLATE = """I want you to act as a SQL terminal in front of an example database, you need only to return the sql command to me.Below is an instruction that describes a task, Write a response that appropriately completes the request.\n"\n##Instruction:\nconcert_singer contains tables such as stadium, singer, concert, singer_in_concert. Table stadium has columns such as Stadium_ID, Location, Name, Capacity, Highest, Lowest, Average. Stadium_ID is the primary key.\nTable singer has columns such as Singer_ID, Name, Country, Song_Name, Song_release_year, Age, Is_male. Singer_ID is the primary key.\nTable concert has columns such as concert_ID, concert_Name, Theme, Stadium_ID, Year. concert_ID is the primary key.\nTable singer_in_concert has columns such as concert_ID, Singer_ID. concert_ID is the primary key.\nThe Stadium_ID of concert is the foreign key of Stadium_ID of stadium.\nThe Singer_ID of singer_in_concert is the foreign key of Singer_ID of singer.\nThe concert_ID of singer_in_concert is the foreign key of concert_ID of concert.\n\n###Input:\n{query}\n\n###Response:""" # noqa: E501
@@ -44,7 +45,7 @@ def do_sample(llm: vllm.LLM, lora_path: str, lora_id: int) -> list[str]:
def test_ilama_lora(ilama_lora_files):
with VllmRunner(model_name=MODEL_PATH,
with VllmRunner(snapshot_download(MODEL_PATH),
enable_lora=True,
max_loras=4,
max_model_len=1024,