From 316ed8aadeffa25dad590f7671eb39c84be0c11b Mon Sep 17 00:00:00 2001 From: Xuan Son Nguyen Date: Tue, 1 Sep 2026 11:59:10 +0200 Subject: [PATCH] nits --- src/llama-hparams.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/src/llama-hparams.h b/src/llama-hparams.h index d43747543d..390d3543d7 100644 --- a/src/llama-hparams.h +++ b/src/llama-hparams.h @@ -161,7 +161,8 @@ struct llama_hparams { // the size of the sliding window (0 - no SWA) uint32_t n_swa = 0; - // deepseek4 vision: when set to non-causal attention, SWA should not be applied (case: input is multimodal) + // deepseek4 vision: when decoding non-causally (multimodal input), SWA is not applied between tokens of the current ubatch (the image span); older tokens are still window-clipped + // for other models (like gemma 3, gemma 4): SWA is always applied to match transformers implementation bool swa_full_non_causal = false; // if is_swa_impl[il] == 1, then layer il is SWA