From 516e8d7a8ab3d231b2c3bf238b3d895970bc769f Mon Sep 17 00:00:00 2001 From: Aman Gupta Date: Tue, 28 Apr 2026 13:41:00 +0800 Subject: [PATCH] server: use pos_next instead of n_tokens for m-rope (#22439) --- tools/server/server-context.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/server/server-context.cpp b/tools/server/server-context.cpp index 08ff1e362..567ddd4f9 100644 --- a/tools/server/server-context.cpp +++ b/tools/server/server-context.cpp @@ -3031,7 +3031,7 @@ private: slot.sampled = ids.back(); // last accepted token SLT_DBG(slot, "add accepted tokens: sampled=%d, ids.size=%zu, n_draft=%zu\n", slot.sampled, ids.size(), n_draft); - llama_memory_seq_rm(llama_get_memory(slot.ctx), slot.id, slot.prompt.n_tokens(), -1); + llama_memory_seq_rm(llama_get_memory(slot.ctx), slot.id, slot.prompt.tokens.pos_next(), -1); for (size_t i = 0; i < ids.size(); ++i) { completion_token_output result;