[Misc] Move print_*_once from utils to logger (#11298)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>
Co-authored-by: Maxime Fournioux <55544262+mfournioux@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2025-01-09 12:48:12 +08:00
committed by GitHub
co-authored by Maxime Fournioux
parent 730e9592e9
commit d848800e88
21 changed files with 129 additions and 72 deletions
@@ -1,8 +1,10 @@
import torch
from vllm.logger import init_logger
from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig, QuantizeMethodBase)
from vllm.utils import print_warning_once
logger = init_logger(__name__)
class BaseKVCacheMethod(QuantizeMethodBase):
@@ -67,7 +69,7 @@ class BaseKVCacheMethod(QuantizeMethodBase):
layer._v_scale = v_scale
if (layer._k_scale == 1.0 and layer._v_scale == 1.0
and "e5m2" not in layer.kv_cache_dtype):
print_warning_once(
logger.warning_once(
"Using KV cache scaling factor 1.0 for fp8_e4m3. This "
"may cause accuracy issues. Please make sure k/v_scale "
"scaling factors are available in the fp8 checkpoint.")