Files
FastDeploy/tests/ci_use/HPU/run_ernie.py
T
FocusLuo c2c1942db9 [INTEL_HPU] [CI] enabled fastdeploy PR testing (#4596)
* [INTEL HPU] added hpu ci work flow support

Signed-off-by: Luo, Focus <focus.luo@intel.com>

* [INTEL HPU] added run ci hpu test scripts

Signed-off-by: Luo, Focus <focus.luo@intel.com>

* [INTEL HPU] enabled HPU ernie test case

Signed-off-by: Luo, Focus <focus.luo@intel.com>

* [INTEL HPU] updated Intel Gaudi Readme with Warmup disable cmdline

Signed-off-by: Luo, Focus <focus.luo@intel.com>

* Modify paddlepaddle installation command

Updated paddlepaddle installation command to use a specific index URL.

* Update run_ci_hpu.sh

* Rename json directory to nlohmann_json

Rename extracted json directory to nlohmann_json.

* Update ci_hpu.yml

* Set pip global index URL to Tsinghua mirror

* Update CI workflow to use self-hosted runner and paths

* Update Docker image in CI workflow

* Modify HPU installation URLs in run_ci_hpu.sh

Updated the installation URL for paddle_intel_hpu and added paddlenlp_ops installation.

* Fix paddle_intel_hpu installation URL

Corrected the URL for paddle_intel_hpu wheel installation.

---------

Signed-off-by: Luo, Focus <focus.luo@intel.com>
Co-authored-by: plusNew001 <95567040+plusNew001@users.noreply.github.com>
2025-11-17 19:24:41 +08:00

47 lines
1.4 KiB
Python

# Copyright (c) 2025 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
import openai
def test_hpu():
ip = "0.0.0.0"
service_http_port = os.getenv("FD_API_PORT", "8388") # service port
client = openai.Client(base_url=f"http://{ip}:{service_http_port}/v1", api_key="EMPTY_API_KEY")
# chat
response = client.chat.completions.create(
model="default",
messages=[
{"role": "user", "content": "The largest ocean is"},
],
temperature=1,
top_p=0,
max_tokens=64,
stream=False,
)
print(f"response is: {response}", flush=True)
generate_context = response.choices[0].message.content
print(f"\ngenerate_context is: {generate_context}", flush=True)
assert "pacific ocean" in generate_context.lower(), "The answer was incorrect!"
print("Test successfully!", flush=True)
if __name__ == "__main__":
test_hpu()