From 2080735e16fca8a6c6c22b064a116c42ece49841 Mon Sep 17 00:00:00 2001
From: Felix Marty <9808326+fxmarty@users.noreply.github.com>
Date: Wed, 19 Jul 2023 16:35:23 +0000
Subject: [PATCH] taste

---
 .../models/custom_modeling/flash_llama_modeling.py             | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/server/text_generation_server/models/custom_modeling/flash_llama_modeling.py b/server/text_generation_server/models/custom_modeling/flash_llama_modeling.py
index cf211ef0..84e22f72 100644
--- a/server/text_generation_server/models/custom_modeling/flash_llama_modeling.py
+++ b/server/text_generation_server/models/custom_modeling/flash_llama_modeling.py
@@ -168,8 +168,7 @@ def _load_gqa(config, prefix: str, weights):
             config.hidden_size,
         ], f"{list(weight.shape)} != {[(num_heads + 2 * config.num_key_value_heads) * head_size, config.hidden_size]}"
 
-    bias = None
-    return TensorParallelColumnLinear(get_linear(weight, bias, config.quantize))
+    return TensorParallelColumnLinear(get_linear(weight, bias=None, quantize=config.quantize))
 
 
 class FlashLlamaAttention(torch.nn.Module):