[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)

Signed-off-by: Chengyi Nie <cnie@roblox.com>
Co-authored-by: Chengyi Nie <cnie@roblox.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Chengyi Nie
2026-05-15 08:25:52 +08:00
committed by GitHub
co-authored by Chengyi Nie Cursor
parent 3b6a204789
commit fa2a33b893
21 changed files with 170 additions and 601 deletions
+2 -3
View File
@@ -44,8 +44,7 @@ from vllm.model_executor.layers.linear import (
RowParallelLinear,
)
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.model_executor.layers.quantization.gptq import GPTQConfig
from vllm.model_executor.layers.quantization.gptq_marlin import GPTQMarlinConfig
from vllm.model_executor.layers.quantization.auto_gptq import AutoGPTQConfig
from vllm.model_executor.layers.rotary_embedding.common import ApplyRotaryEmb
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.model_executor.models.interfaces import (
@@ -883,7 +882,7 @@ class OpenPanguVLForConditionalGeneration(
self.image_std = tuple(image_processor.image_std)
def _maybe_ignore_quant_config(self, quant_config: QuantizationConfig):
if isinstance(quant_config, (GPTQConfig, GPTQMarlinConfig)):
if isinstance(quant_config, AutoGPTQConfig):
return None
return quant_config