From d228bf8552f5a6afa0f4c523c0da4bc00312b791 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Tue, 23 Apr 2024 17:32:11 +0300 Subject: [PATCH] cont --- llama.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama.cpp b/llama.cpp index fcd15501e..a3624544c 100644 --- a/llama.cpp +++ b/llama.cpp @@ -15092,7 +15092,7 @@ struct llama_context * llama_new_context_with_model( // ref: https://github.com/ggerganov/llama.cpp/pull/5021 if (cparams.n_batch < GGML_KQ_MASK_PAD) { LLAMA_LOG_WARN("%s: n_batch is less than GGML_KQ_MASK_PAD - increasing to %d\n", __func__, GGML_KQ_MASK_PAD); - cparams.n_batch = std::max((uint32_t) GGML_KQ_MASK_PAD, params.n_batch); + cparams.n_batch = GGML_KQ_MASK_PAD; } cparams.n_ubatch = std::min(cparams.n_batch, params.n_ubatch == 0 ? params.n_batch : params.n_ubatch);