wassname/vllm
1
0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-09-12 13:01:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add GPTQ support (#916)

Browse Source
This commit is contained in:
CHU Tianxiang
2023-12-15 03:04:22 -08:00
committed by GitHub
parent c06170cc8e
commit 0fbfc4b81b
35 changed files with 1782 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vllm/model_executor/layers/quantization/__init__.py
+4 -2
View File
@@ -1,11 +1,13 @@
from typing import Type
from vllm.model_executor.layers.quantization.awq import AWQConfig
from vllm.model_executor.layers.quantization.squeezellm import SqueezeLLMConfig
from vllm.model_executor.layers.quantization.base_config import QuantizationConfig
from vllm.model_executor.layers.quantization.awq import AWQConfig
from vllm.model_executor.layers.quantization.gptq import GPTQConfig
from vllm.model_executor.layers.quantization.squeezellm import SqueezeLLMConfig
_QUANTIZATION_CONFIG_REGISTRY = {
"awq": AWQConfig,
"gptq": GPTQConfig,
"squeezellm": SqueezeLLMConfig,
}