matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-12 00:37:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

update llama.cpp submodule to 6cdabe6 (#2999)

Browse Source
This commit is contained in:
Jeffrey Morgan
2024-03-08 00:26:20 -08:00
committed by GitHub
parent b886bec3f9
commit 0e4669b04f
4 changed files with 32 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -1,21 +1,19 @@
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 2b2f4a0f..afac49af 100644
index f255ad76..914ecfdd 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -997,13 +997,15 @@ struct llama_server_context
slot.n_sent_text += result.text_to_send.size();
@@ -1101,12 +1101,13 @@ struct server_context {
// 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;
}