mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-09 09:45:34 +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>
77 lines
2.5 KiB
Python
77 lines
2.5 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
"""
|
|
Saves each worker's model state dict directly to a checkpoint, which enables a
|
|
fast load path for large tensor-parallel models where each worker only needs to
|
|
read its own shard rather than the entire checkpoint.
|
|
|
|
Example usage:
|
|
|
|
python save_sharded_state.py \
|
|
--model /path/to/load \
|
|
--quantization deepspeedfp \
|
|
--tensor-parallel-size 8 \
|
|
--output /path/to/save
|
|
|
|
Then, the model can be loaded with
|
|
|
|
llm = LLM(
|
|
model="/path/to/save",
|
|
load_format="sharded_state",
|
|
quantization="deepspeedfp",
|
|
tensor_parallel_size=8,
|
|
)
|
|
"""
|
|
import dataclasses
|
|
import os
|
|
import shutil
|
|
from pathlib import Path
|
|
|
|
from vllm import LLM, EngineArgs
|
|
from vllm.utils import FlexibleArgumentParser
|
|
|
|
parser = FlexibleArgumentParser()
|
|
EngineArgs.add_cli_args(parser)
|
|
parser.add_argument("--output",
|
|
"-o",
|
|
required=True,
|
|
type=str,
|
|
help="path to output checkpoint")
|
|
parser.add_argument("--file-pattern",
|
|
type=str,
|
|
help="string pattern of saved filenames")
|
|
parser.add_argument("--max-file-size",
|
|
type=str,
|
|
default=5 * 1024**3,
|
|
help="max size (in bytes) of each safetensors file")
|
|
|
|
|
|
def main(args):
|
|
engine_args = EngineArgs.from_cli_args(args)
|
|
if engine_args.enable_lora:
|
|
raise ValueError("Saving with enable_lora=True is not supported!")
|
|
model_path = engine_args.model
|
|
if not Path(model_path).is_dir():
|
|
raise ValueError("model path must be a local directory")
|
|
# Create LLM instance from arguments
|
|
llm = LLM(**dataclasses.asdict(engine_args))
|
|
# Prepare output directory
|
|
Path(args.output).mkdir(exist_ok=True)
|
|
# Dump worker states to output directory
|
|
model_executor = llm.llm_engine.model_executor
|
|
model_executor.save_sharded_state(path=args.output,
|
|
pattern=args.file_pattern,
|
|
max_size=args.max_file_size)
|
|
# Copy metadata files to output directory
|
|
for file in os.listdir(model_path):
|
|
if os.path.splitext(file)[1] not in (".bin", ".pt", ".safetensors"):
|
|
if os.path.isdir(os.path.join(model_path, file)):
|
|
shutil.copytree(os.path.join(model_path, file),
|
|
os.path.join(args.output, file))
|
|
else:
|
|
shutil.copy(os.path.join(model_path, file), args.output)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
args = parser.parse_args()
|
|
main(args)
|