Add GPTQ support (#916)

2023-12-15 19:04:22 +08:00
parent c06170cc8e
commit 0fbfc4b81b
35 changed files with 1782 additions and 82 deletions
--- a/vllm/model_executor/layers/quantization/init.py
+++ b/vllm/model_executor/layers/quantization/init.py
@@ -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,
 }