Add GPTQ support (#916)

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
+3 -2
View File
@@ -38,8 +38,9 @@ class LLM:
However, if the `torch_dtype` in the config is `float32`, we will
use `float16` instead.
quantization: The method used to quantize the model weights. Currently,
we support "awq". If None, we assume the model weights are not
quantized and use `dtype` to determine the data type of the weights.
we support "awq", "gptq" and "squeezellm". If None, we assume the
model weights are not quantized and use `dtype` to determine the
data type of the weights.
revision: The specific model version to use. It can be a branch name,
a tag name, or a commit id.
tokenizer_revision: The specific tokenizer version to use. It can be a