diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 0db99c167..92a1090f7 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -1555,10 +1555,6 @@ struct llama_server_context // we have to evaluate at least 1 token to generate logits. LOG_TEE("slot %d : we have to evaluate at least 1 token to generate logits\n", slot.id); slot.n_past--; - if(slot.n_past_self_extension > 0) - { - slot.n_past_self_extension--; - } } LOG_VERBOSE("prompt ingested", { @@ -1613,12 +1609,6 @@ struct llama_server_context return true; } - std::vector slot_npasts; - for (auto & slot : slots) - { - slot_npasts.emplace_back(0); - } - for (int32_t i = 0; i < (int32_t) batch.n_tokens; i += n_batch) { const int32_t n_tokens = std::min(n_batch, (int32_t) (batch.n_tokens - i));