[Bugfix] Get available quantization methods from quantization registry (#4098)

This commit is contained in:
Michael Goin
2024-04-18 00:21:55 -07:00
committed by GitHub
parent 66ded03067
commit 53b018edcb
6 changed files with 18 additions and 13 deletions
+2 -1
View File
@@ -9,6 +9,7 @@ import torch
from tqdm import tqdm
from vllm import LLM, SamplingParams
from vllm.model_executor.layers.quantization import QUANTIZATION_METHODS
def main(args: argparse.Namespace):
@@ -101,7 +102,7 @@ if __name__ == '__main__':
parser.add_argument('--tokenizer', type=str, default=None)
parser.add_argument('--quantization',
'-q',
choices=['awq', 'gptq', 'squeezellm', None],
choices=[*QUANTIZATION_METHODS, None],
default=None)
parser.add_argument('--tensor-parallel-size', '-tp', type=int, default=1)
parser.add_argument('--input-len', type=int, default=32)