baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Update llama.cpp gguf to latest (#710)

Browse source
This commit is contained in:
Bruce MacDonald 2023-10-17 16:55:16 -04:00 committed by GitHub
parent bd93a94abd
commit f3648fd206
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 10 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
llm/llama.cpp/gguf

@ -1 +1 @@
Subproject commit bc9d3e3971e5607a10ff4c24e39568ce1ac87271 Subproject commit 40e5ce054f4c4fa555e4510ea5f760bb29185332

18
llm/llama.cpp/patches/0001-remove-warm-up-logging.patch
View file

@ -1,6 +1,6 @@
From 07993bdc35345b67b27aa649a7c099ad42d80c4c Mon Sep 17 00:00:00 2001 From 8dbb5449db259a9c24796e7927d89bee98b6c8f5 Mon Sep 17 00:00:00 2001
From: Michael Yang <mxyng@pm.me> From: Bruce MacDonald <brucewmacdonald@gmail.com>
Date: Thu, 21 Sep 2023 14:43:21 -0700 Date: Thu, 5 Oct 2023 11:21:12 -0400
Subject: [PATCH] remove warm up logging Subject: [PATCH] remove warm up logging
--- ---
@ -8,18 +8,18 @@ Subject: [PATCH] remove warm up logging
1 file changed, 2 deletions(-) 1 file changed, 2 deletions(-)
diff --git a/common/common.cpp b/common/common.cpp diff --git a/common/common.cpp b/common/common.cpp
index 2597ba0..b56549b 100644 index 7370017..c4433fe 100644
--- a/common/common.cpp --- a/common/common.cpp
+++ b/common/common.cpp +++ b/common/common.cpp
@@ -780,8 +780,6 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par @@ -839,8 +839,6 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
} }
{ {
- LOG("warming up the model with an empty run\n"); - LOG("warming up the model with an empty run\n");
- -
const std::vector<llama_token> tmp = { llama_token_bos(lctx), llama_token_eos(lctx), }; std::vector<llama_token> tmp = { llama_token_bos(lctx), llama_token_eos(lctx), };
llama_eval(lctx, tmp.data(), std::min(tmp.size(), (size_t) params.n_batch), 0, params.n_threads); llama_decode(lctx, llama_batch_get_one(tmp.data(), std::min(tmp.size(), (size_t) params.n_batch), 0, 0));
llama_reset_timings(lctx); llama_kv_cache_tokens_rm(lctx, -1, -1);
-- --
2.42.0 2.39.2 (Apple Git-143)