xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-15 03:37:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Fix arg names in quantizer script (#5507)

Browse Source
This commit is contained in:
Allen.Dou 2024-06-14 10:02:53 +08:00 committed by GitHub
parent cd9c0d65d9
commit 55d6361b13
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
examples/fp8/quantizer/quantize.py
View File

@ -332,7 +332,7 @@ def main(args):
if __name__ == "__main__": if __name__ == "__main__":
parser = argparse.ArgumentParser(description=__doc__) parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--model_dir", parser.add_argument("--model-dir",
help="Specify where the HuggingFace model is", help="Specify where the HuggingFace model is",
required=True) required=True)
parser.add_argument("--device", default="cuda") parser.add_argument("--device", default="cuda")
@ -346,19 +346,19 @@ if __name__ == "__main__":
"full_prec" "full_prec"
], ],
) )
parser.add_argument("--batch_size", parser.add_argument("--batch-size",
help="Batch size for calibration.", help="Batch size for calibration.",
type=int, type=int,
default=1) default=1)
parser.add_argument("--calib_size", parser.add_argument("--calib-size",
help="Number of samples for calibration.", help="Number of samples for calibration.",
type=int, type=int,
default=512) default=512)
parser.add_argument("--output_dir", default="exported_model") parser.add_argument("--output-dir", default="exported_model")
parser.add_argument("--tp_size", type=int, default=1) parser.add_argument("--tp-size", type=int, default=1)
parser.add_argument("--pp_size", type=int, default=1) parser.add_argument("--pp-size", type=int, default=1)
parser.add_argument("--awq_block_size", type=int, default=128) parser.add_argument("--awq-block-size", type=int, default=128)
parser.add_argument("--kv_cache_dtype", parser.add_argument("--kv-cache-dtype",
help="KV Cache dtype.", help="KV Cache dtype.",
default=None, default=None,
choices=["int8", "fp8", None]) choices=["int8", "fp8", None])