From 6693df846c863e7764c59a377a29f2e9f133ad75 Mon Sep 17 00:00:00 2001 From: Daniel Bevenius Date: Fri, 6 Feb 2026 13:15:20 +0100 Subject: [PATCH] examples : set n_seq_max = 2 for ctx3 This commit updates the save-load-state example to set the n_seq_max parameter to 2 when initializing the ctx3 context. The motivation for this change is that using 1 as n_parallel/n_seq_max the context only supports one sequence, but the test laster tries to use a second sequence which results in the following error: ```console main : loaded state with 4 tokens main : seq 0 copied, 225760 bytes main : kv cache cleared find_slot: seq_id=1 >= n_seq_max=1 Try using a bigger --parallel value state_read_meta: failed to find available cells in kv cache ``` This seems to only happen for recurrent/hybrid models. --- examples/save-load-state/save-load-state.cpp | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/examples/save-load-state/save-load-state.cpp b/examples/save-load-state/save-load-state.cpp index 8b111a2ca8..c315933163 100644 --- a/examples/save-load-state/save-load-state.cpp +++ b/examples/save-load-state/save-load-state.cpp @@ -151,7 +151,9 @@ int main(int argc, char ** argv) { } // make new context - llama_context * ctx3 = llama_init_from_model(model, common_context_params_to_llama(params)); + auto params_ctx3 = common_context_params_to_llama(params); + params_ctx3.n_seq_max = 2; + llama_context * ctx3 = llama_init_from_model(model, params_ctx3); llama_sampler * smpl3 = llama_sampler_chain_init(sparams);