From 21431197a1c7d04cd95fae4360667be1177d1dd9 Mon Sep 17 00:00:00 2001 From: Leon Ericsson Date: Sat, 16 Dec 2023 12:12:33 +0100 Subject: [PATCH] kv_cache management --- examples/lookup/lookup.cpp | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/examples/lookup/lookup.cpp b/examples/lookup/lookup.cpp index a9347e51e..28b9c2c95 100644 --- a/examples/lookup/lookup.cpp +++ b/examples/lookup/lookup.cpp @@ -130,6 +130,10 @@ int main(int argc, char ** argv){ break; } + // KV cache management + // clean the cache of draft tokens that weren't accepted + llama_kv_cache_seq_rm(ctx, 0, n_past, -1); + llama_batch_clear(batch_tgt); llama_batch_add(batch_tgt, draft[0], n_past, { 0 }, true);