From 96a982ad8fc232479384476b1596a880697cc1d0 Mon Sep 17 00:00:00 2001
From: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
Date: Wed, 25 Oct 2023 10:18:58 +0200
Subject: [PATCH] fix: better warmup error

---
 server/text_generation_server/models/flash_causal_lm.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/server/text_generation_server/models/flash_causal_lm.py b/server/text_generation_server/models/flash_causal_lm.py
index 1fe40c0c520..f1a4854f9ea 100644
--- a/server/text_generation_server/models/flash_causal_lm.py
+++ b/server/text_generation_server/models/flash_causal_lm.py
@@ -670,7 +670,7 @@ def warmup(self, batch: FlashCausalLMBatch):
                 self.device,
             )
             _, batch = self.generate_token(batch)
-        except Exception as e:
+        except torch.cuda.OutOfMemoryError as e:
             raise RuntimeError(
                 f"Not enough memory to handle {len(batch.input_ids)} prefill tokens. "
                 f"You need to decrease `--max-batch-prefill-tokens`"