CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into gg/llama-kv-cache

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-02-18 10:14:37 +02:00
parent 1d801d27b9 73e2ed3ce3
commit f0d3ff2388
156 changed files with 6433 additions and 2603 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/server/tests/utils.py
View File

@@ -78,6 +78,7 @@ class ServerProcess:
draft_max: int | None = None
no_webui: bool | None = None
jinja: bool | None = None
reasoning_format: Literal['deepseek', 'none'] | None = None
chat_template: str | None = None
chat_template_file: str | None = None
@@ -172,6 +173,8 @@ class ServerProcess:
server_args.append("--no-webui")
if self.jinja:
server_args.append("--jinja")
if self.reasoning_format is not None:
server_args.extend(("--reasoning-format", self.reasoning_format))
if self.chat_template:
server_args.extend(["--chat-template", self.chat_template])
if self.chat_template_file: