From 66d8eccd42b5b5b2179c60a6d41376d3917f3b40 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Tue, 4 Nov 2025 19:21:36 +0200 Subject: [PATCH] server : do context shift only while generating (#17000) --- tools/server/server.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/server/server.cpp b/tools/server/server.cpp index ec7dc1a130..678aad93b8 100644 --- a/tools/server/server.cpp +++ b/tools/server/server.cpp @@ -3587,7 +3587,7 @@ struct server_context { // apply context-shift if needed // TODO: simplify and improve for (server_slot & slot : slots) { - if (slot.is_processing() && slot.prompt.n_tokens() + 1 >= slot.n_ctx) { + if (slot.state == SLOT_STATE_GENERATING && slot.prompt.n_tokens() + 1 >= slot.n_ctx) { if (!params_base.ctx_shift) { // this check is redundant (for good) // we should never get here, because generation should already stopped in process_token()