add 2/3/5/6/7 CUDA support in AutoRound format (#52890)
Signed-off-by: Wenhua Cheng <wenhua.cheng@intel.com>
This commit is contained in:
@@ -34,9 +34,8 @@ class INCConfig(QuantizationConfig):
|
||||
Repo: https://github.com/intel/neural-compressor
|
||||
"""
|
||||
|
||||
SUPPORTED_BITS = {2, 3, 4, 5, 6, 7, 8}
|
||||
DEFAULT_INT_PACKING_FORMAT = "auto_round:auto_gptq"
|
||||
|
||||
SUPPORTED_BITS = {2, 3, 4, 8}
|
||||
SUPPORTED_DTYPES = {"int", "mx_fp", "fp"}
|
||||
SUPPORTED_FORMATS = {
|
||||
"auto_round:auto_gptq",
|
||||
|
||||
Reference in New Issue
Block a user