From 487a5e0401423bba02cd6e97e4d45131bb20b22b Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Fri, 6 Jun 2025 13:29:18 +0300 Subject: [PATCH] context : fix SWA-related warning for multiple sequences (#14045) --- src/llama-context.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/llama-context.cpp b/src/llama-context.cpp index d94bf864..ea191068 100644 --- a/src/llama-context.cpp +++ b/src/llama-context.cpp @@ -123,7 +123,7 @@ llama_context::llama_context( __func__, n_ctx_per_seq, hparams.n_ctx_train); } - if (!params.swa_full && cparams.n_seq_max > 1) { + if (!params.swa_full && cparams.n_seq_max > 1 && hparams.is_swa_any()) { LLAMA_LOG_WARN("%s: requested n_seq_max (%u) > 1, but swa_full is not enabled -- performance may be degraded: %s\n", __func__, cparams.n_seq_max, "https://github.com/ggml-org/llama.cpp/pull/13845#issuecomment-2924800573"); }