From aac91d1d262a2688e08e223c7ecf2bb404fdd995 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Tue, 10 Sep 2024 18:00:21 +0200 Subject: [PATCH] Updating VLM causal model with updated context. --- server/text_generation_server/models/vlm_causal_lm.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/server/text_generation_server/models/vlm_causal_lm.py b/server/text_generation_server/models/vlm_causal_lm.py index d6cb36fa..7f7d2e4d 100644 --- a/server/text_generation_server/models/vlm_causal_lm.py +++ b/server/text_generation_server/models/vlm_causal_lm.py @@ -367,9 +367,7 @@ class VlmCausalLM(FlashCausalLM): with self._forward_context( block_tables=block_tables, cu_seqlen_prefill=cu_seqlen_prefill, - input_lengths=batch.input_lengths, input_lengths_tensor=input_lengths, - prefix_lens=batch.prefix_lens, prefix_lens_tensor=prefix_lens_tensor, ): max_k = (input_lengths + prefix_lens_tensor).max().item()