mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-22 09:35:52 +08:00
e489ad7a21
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com>
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>
55 lines
2.1 KiB
Python
55 lines
2.1 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
from typing import List
|
|
|
|
import pytest
|
|
|
|
import vllm
|
|
from vllm.lora.request import LoRARequest
|
|
|
|
MODEL_PATH = "ibm-granite/granite-3b-code-base"
|
|
|
|
|
|
def do_sample(llm: vllm.LLM, lora_path: str, lora_id: int) -> List[str]:
|
|
prompts = [
|
|
"[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE candidate (people_id VARCHAR, unsure_rate INTEGER); CREATE TABLE people (sex VARCHAR, people_id VARCHAR)\n\n question: which gender got the highest average uncertain ratio. [/user] [assistant]", # noqa: E501
|
|
"[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_28138035_4 (womens_doubles VARCHAR, mens_singles VARCHAR)\n\n question: Name the women's doubles for werner schlager [/user] [assistant]" # noqa: E501
|
|
]
|
|
sampling_params = vllm.SamplingParams(temperature=0,
|
|
max_tokens=256,
|
|
stop=["[/assistant]"])
|
|
outputs = llm.generate(
|
|
prompts,
|
|
sampling_params,
|
|
lora_request=LoRARequest(str(lora_id), lora_id, lora_path)
|
|
if lora_id else None)
|
|
generated_texts: List[str] = []
|
|
for output in outputs:
|
|
generated_text = output.outputs[0].text
|
|
generated_texts.append(generated_text)
|
|
return generated_texts
|
|
|
|
|
|
@pytest.mark.parametrize("lora_bias", [True])
|
|
@pytest.mark.parametrize("fully_sharded", [True, False])
|
|
def test_lora_bias(lora_bias_files: str, lora_bias: bool, fully_sharded: bool):
|
|
llm = vllm.LLM(MODEL_PATH,
|
|
enable_lora=True,
|
|
max_num_seqs=16,
|
|
max_lora_rank=8,
|
|
max_loras=1,
|
|
enable_lora_bias=lora_bias,
|
|
tensor_parallel_size=1,
|
|
fully_sharded_loras=fully_sharded)
|
|
|
|
print("lora adapter created")
|
|
output1 = do_sample(llm, lora_bias_files, lora_id=0)
|
|
|
|
print("lora")
|
|
output2 = do_sample(llm, lora_bias_files, lora_id=1)
|
|
|
|
if lora_bias:
|
|
assert output1 != output2
|
|
else:
|
|
assert output1 == output2
|