[Hardware][XPU] AWQ/GPTQ support for xpu backend (#10107)

Signed-off-by: yan ma <yan.ma@intel.com>
This commit is contained in:
Yan Ma
2024-11-18 11:18:05 -07:00
committed by GitHub
parent 281cc4b3cd
commit 6b2d25efc7
7 changed files with 146 additions and 52 deletions
@@ -23,6 +23,7 @@ from vllm.model_executor.parameter import (ChannelQuantScaleParameter,
PackedColumnParameter,
PackedvLLMParameter,
RowvLLMParameter)
from vllm.platforms import current_platform
from vllm.scalar_type import scalar_types
logger = init_logger(__name__)
@@ -134,6 +135,9 @@ class GPTQMarlinConfig(QuantizationConfig):
sym = quant_config.get("sym")
desc_act = quant_config.get("desc_act")
if not current_platform.is_cuda():
return False
if quant_method != "gptq":
return False