Support SqueezeLLM (#1326)

Co-authored-by: squeeze-ai-lab <squeezeailab.bair@gmail.com> Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2023-10-22 03:14:59 -03:00
parent bf31d3606a
commit 1f24755bf8
16 changed files with 378 additions and 40 deletions
--- a/vllm/engine/arg_utils.py
+++ b/vllm/engine/arg_utils.py
@@ -168,7 +168,7 @@ class EngineArgs:
        parser.add_argument('--quantization',
                            '-q',
                            type=str,
-                            choices=['awq', None],
+                            choices=['awq', 'squeezellm', None],
                            default=None,
                            help='Method used to quantize the weights')
        return parser