matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-12 08:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

update llama.cpp submodule to ceca1ae (#3064)

Browse Source
This commit is contained in:
Jeffrey Morgan
2024-03-11 12:57:48 -07:00
committed by GitHub
parent f878e91070
commit 369eda65f5
6 changed files with 36 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
llm/patches/01-cache.diff
View File

@@ -1,19 +1,21 @@
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index f255ad76..914ecfdd 100644
index 8fe5e0b1..3e82acb9 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -1101,12 +1101,13 @@ struct server_context {
@@ -997,13 +997,15 @@ struct llama_server_context
slot.n_sent_text += result.text_to_send.size();
// add the token to slot queue and cache
}
- slot.add_token_string(result);
if (slot.params.stream) {
+
if (slot.params.stream)
{
send_partial_response(slot, result);
}
}
+ slot.add_token_string(result);
+
if (incomplete) {
if (incomplete)
{
slot.has_next_token = true;
}