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

[Model][Quantization] HQQ support through Marlin kernel expansion (#9766)

Browse Source 
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
This commit is contained in:
ElizaWszola
2024-11-19 22:31:12 +01:00
committed by GitHub
parent efa9084628
commit b00b33d77e
11 changed files with 632 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/quantization/__init__.py
View File

@@ -21,6 +21,7 @@ from vllm.model_executor.layers.quantization.gptq_marlin import (
GPTQMarlinConfig)
from vllm.model_executor.layers.quantization.gptq_marlin_24 import (
GPTQMarlin24Config)
from vllm.model_executor.layers.quantization.hqq_marlin import HQQMarlinConfig
from vllm.model_executor.layers.quantization.ipex_quant import IPEXConfig
from vllm.model_executor.layers.quantization.marlin import MarlinConfig
from vllm.model_executor.layers.quantization.modelopt import ModelOptFp8Config
@@ -48,6 +49,7 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
"compressed-tensors": CompressedTensorsConfig,
"bitsandbytes": BitsAndBytesConfig,
"qqq": QQQConfig,
"hqq": HQQMarlinConfig,
"experts_int8": ExpertsInt8Config,
"neuron_quant": NeuronQuantConfig,
"ipex": IPEXConfig,