From ce903c03848c5a033f0ce9ab6ed2c59ca4bed4ab Mon Sep 17 00:00:00 2001
From: kijai <40791699+kijai@users.noreply.github.com>
Date: Mon, 28 Oct 2024 04:07:11 +0200
Subject: [PATCH] Update mz_gguf_loader.py

---
 mz_gguf_loader.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mz_gguf_loader.py b/mz_gguf_loader.py
index ca3a913..e37d308 100644
--- a/mz_gguf_loader.py
+++ b/mz_gguf_loader.py
@@ -27,6 +27,7 @@ def quantize_load_state_dict(model, state_dict, device="cpu", cublas_ops=False):
             setattr(model, "cublas_half_matmul", True)
             print("Using cublas_ops")
         except:
+            print("Failed to load cublas_ops")
             raise ImportError("Install cublas_ops (https://github.com/aredden/torch-cublas-hgemm) to use cublas_ops")
     else:
         linear_ops = F.linear