[Quant][Kernel] Remove GPTQ Group/Dynamic Activation Ordering (#54809)
Signed-off-by: Roderick-Wu <roderickwu2003@gmail.com> Signed-off-by: Roderick Wu <roderickwu2003@gmail.com> Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
@@ -17,8 +17,7 @@ from vllm.model_executor.layers.vocab_parallel_embedding import (
|
||||
PROMPT = "On the surface of Mars, we found"
|
||||
|
||||
MODELS_QUANT = [
|
||||
("ModelCloud/Qwen1.5-1.8B-Chat-GPTQ-4bits-dynamic-cfg-with-lm_head", True),
|
||||
("TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ", False),
|
||||
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", False),
|
||||
]
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user