From 83008b7cfe90ad89d0c0ed2c2424fd75edc25ac1 Mon Sep 17 00:00:00 2001 From: Daniel Bevenius Date: Tue, 10 Sep 2024 09:03:21 +0200 Subject: [PATCH] llama : update llm_build_copy_mask_state comment [no ci] (#9385) This commit updates the comment, which seems to contain a typo or be an outdated comment, in the copy_mask_state function changing the variable n_rs to n_kv. I believe this change is correct and what the comment wants to convey is to copy the states that are not going to be used in the upcoming processing, which are the tokens states from n_seqs up to the number of possible token states n_kv. --- src/llama.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/llama.cpp b/src/llama.cpp index ee27cbd1c..40db03517 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -9258,7 +9258,7 @@ static struct ggml_tensor * llm_build_copy_mask_state( // FIXME: zero-out NANs? states = ggml_mul(ctx, states, state_mask); - // copy states which won't be changed further (between n_seqs and n_rs) + // copy states which won't be changed further (between n_seqs and n_kv) ggml_build_forward_expand(graph, ggml_cpy(ctx, ggml_view_1d(ctx, states, n_state*(n_kv - n_seqs), n_seqs*n_state*ggml_element_size(states)),