From 64569135b25258cd283f8913ec1c63b7ae7588a7 Mon Sep 17 00:00:00 2001
From: Maxim <makc.anufriev@gmail.com>
Date: Tue, 28 Oct 2025 16:53:45 -0300
Subject: [PATCH] Remove unnecessary CUDA cache clearing - no memory leak
 reproducible now.

---
 model/kronos.py | 2 --
 1 file changed, 2 deletions(-)

diff --git a/model/kronos.py b/model/kronos.py
index e95a853..5e1c336 100644
--- a/model/kronos.py
+++ b/model/kronos.py
@@ -432,8 +432,6 @@ def auto_regressive_inference(tokenizer, model, x, x_stamp, y_stamp, max_context
             x_token[0] = torch.cat([x_token[0], sample_pre], dim=1)
             x_token[1] = torch.cat([x_token[1], sample_post], dim=1)
 
-            torch.cuda.empty_cache()
-
         input_tokens = [t[:, -max_context:].contiguous() for t in x_token]
         z = tokenizer.decode(input_tokens, half=True)
         z = z.reshape(batch_size, sample_count, z.size(1), z.size(2))