CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-05 09:36:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

tests : add unified cache server tests

Browse Source
This commit is contained in:
Georgi Gerganov
2025-10-23 16:24:57 +03:00
parent 6089e08b00
commit f3d1607579
2 changed files with 34 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -78,6 +78,7 @@ class ServerProcess:
server_embeddings: bool | None = False
server_reranking: bool | None = False
server_metrics: bool | None = False
kv_unified: bool | None = False
server_slots: bool | None = False
pooling: str | None = None
draft: int | None = None
@@ -159,6 +160,8 @@ class ServerProcess:
server_args.append("--reranking")
if self.server_metrics:
server_args.append("--metrics")
if self.kv_unified:
server_args.append("--kv-unified")
if self.server_slots:
server_args.append("--slots")
else: