From 2967b8168c3788c2d8e009c7c5b16e3b6a01a667 Mon Sep 17 00:00:00 2001
From: fxmarty <9808326+fxmarty@users.noreply.github.com>
Date: Tue, 16 Jul 2024 15:16:27 +0200
Subject: [PATCH] fix post refactor

---
 server/text_generation_server/utils/quantization.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/server/text_generation_server/utils/quantization.py b/server/text_generation_server/utils/quantization.py
index 07975bea..29782321 100644
--- a/server/text_generation_server/utils/quantization.py
+++ b/server/text_generation_server/utils/quantization.py
@@ -77,7 +77,11 @@ def _get_quantizer_config(model_id, revision):
                 if "version" in data and data["version"] == "GEMM":
                     quant_method = "awq"
             except Exception:
-                pass
+                if self.quant_method is None:
+                    if "awq" in model_id.lower():
+                        self.quant_method = "awq"
+                    elif "gptq" in model_id.lower():
+                        self.quant_method = "gptq"
 
     return _QuantizerConfig(
         bits=bits,