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

[Misc] Remove SqueezeLLM (#8220)

Browse Source
This commit is contained in:
Dipika Sikka
2024-09-06 18:29:03 -04:00
committed by GitHub
parent 9db52eab3d
commit 23f322297f
12 changed files with 6 additions and 389 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -25,7 +25,6 @@ from vllm.model_executor.layers.quantization.marlin import MarlinConfig
from vllm.model_executor.layers.quantization.neuron_quant import (
NeuronQuantConfig)
from vllm.model_executor.layers.quantization.qqq import QQQConfig
from vllm.model_executor.layers.quantization.squeezellm import SqueezeLLMConfig
from vllm.model_executor.layers.quantization.tpu_int8 import Int8TpuConfig
QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
@@ -43,7 +42,6 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
"gptq_marlin": GPTQMarlinConfig,
"awq_marlin": AWQMarlinConfig,
"gptq": GPTQConfig,
"squeezellm": SqueezeLLMConfig,
"compressed-tensors": CompressedTensorsConfig,
"bitsandbytes": BitsAndBytesConfig,
"qqq": QQQConfig,