biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Improve configs - ModelConfig (#17130)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-04-30 03:38:22 +01:00
committed by GitHub
parent 2c4f59afc3
commit 13698db634
36 changed files with 490 additions and 648 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/model_executor/layers/quantization/gptq_marlin.py
View File

@@ -11,6 +11,7 @@ from vllm.model_executor.layers.fused_moe.layer import (
FusedMoE, FusedMoEMethodBase, FusedMoeWeightScaleSupported)
from vllm.model_executor.layers.linear import (LinearMethodBase,
set_weight_attrs)
from vllm.model_executor.layers.quantization import QuantizationMethods
from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig, QuantizeMethodBase)
from vllm.model_executor.layers.quantization.kernels.mixed_precision import (
@@ -100,7 +101,7 @@ class GPTQMarlinConfig(QuantizationConfig):
f"dynamic={self.dynamic}")
@classmethod
def get_name(cls) -> str:
def get_name(cls) -> QuantizationMethods:
return "gptq_marlin"
@classmethod
@@ -130,8 +131,8 @@ class GPTQMarlinConfig(QuantizationConfig):
lm_head_quantized, dynamic, config)
@classmethod
def override_quantization_method(cls, hf_quant_cfg,
user_quant) -> Optional[str]:
def override_quantization_method(
cls, hf_quant_cfg, user_quant) -> Optional[QuantizationMethods]:
can_convert = cls.is_gptq_marlin_compatible(hf_quant_cfg)
is_valid_user_quant = (user_quant is None or user_quant == "marlin"