From 48067e4a0dd23a7471cf8714356f0a5dd5256b31 Mon Sep 17 00:00:00 2001 From: "Wang, Yi A" Date: Mon, 13 Jan 2025 17:23:28 -0800 Subject: [PATCH] fmt Signed-off-by: Wang, Yi A --- server/text_generation_server/models/flash_causal_lm.py | 4 +++- 1 file changed, 3 insertions(+), 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 739319f8..4baa3eda 100644 --- a/server/text_generation_server/models/flash_causal_lm.py +++ b/server/text_generation_server/models/flash_causal_lm.py @@ -1595,7 +1595,9 @@ class FlashCausalLM(Model): if max_total_tokens is None: if get_support_chunking(): model_max_length = self.tokenizer.model_max_length - max_position_embeddings = getattr(self.config, "max_position_embeddings", model_max_length) + max_position_embeddings = getattr( + self.config, "max_position_embeddings", model_max_length + ) max_total_tokens = min( num_blocks * BLOCK_SIZE, model_max_length, max_position_embeddings )