Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
OpenDAS
ollama
Commits
f3648fd2
Unverified
Commit
f3648fd2
authored
Oct 17, 2023
by
Bruce MacDonald
Committed by
GitHub
Oct 17, 2023
Browse files
Update llama.cpp gguf to latest (#710)
parent
bd93a94a
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
10 additions
and
10 deletions
+10
-10
llm/llama.cpp/gguf
llm/llama.cpp/gguf
+1
-1
llm/llama.cpp/patches/0001-remove-warm-up-logging.patch
llm/llama.cpp/patches/0001-remove-warm-up-logging.patch
+9
-9
No files found.
gguf
@
40e5ce05
Compare
bc9d3e39
...
40e5ce05
Subproject commit
bc9d3e3971e5607a10ff4c24e39568ce1ac87271
Subproject commit
40e5ce054f4c4fa555e4510ea5f760bb29185332
llm/llama.cpp/patches/0001-remove-warm-up-logging.patch
View file @
f3648fd2
From
07993bdc35345b67b27aa649a7c099ad42d80c4c
Mon Sep 17 00:00:00 2001
From:
Michael Yang <mxyng@pm.me
>
Date: Thu,
21 Sep
2023 1
4:43:21
-0
7
00
From
8dbb5449db259a9c24796e7927d89bee98b6c8f5
Mon Sep 17 00:00:00 2001
From:
Bruce MacDonald <brucewmacdonald@gmail.com
>
Date: Thu,
5 Oct
2023 1
1:21:12
-0
4
00
Subject: [PATCH] remove warm up logging
---
...
...
@@ -8,18 +8,18 @@ Subject: [PATCH] remove warm up logging
1 file changed, 2 deletions(-)
diff --git a/common/common.cpp b/common/common.cpp
index
2597ba0..b56549b
100644
index
7370017..c4433fe
100644
--- a/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");
-
const
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_
reset_timings(lctx
);
std::vector<llama_token> tmp = { llama_token_bos(lctx), llama_token_eos(lctx), };
llama_
decode
(lctx,
llama_batch_get_one(
tmp.data(), std::min(tmp.size(), (size_t) params.n_batch), 0,
0)
);
llama_
kv_cache_tokens_rm(lctx, -1, -1
);
--
2.
42.0
2.
39.2 (Apple Git-143)
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment