From 76a82babef9703b814ae4cea28cc63c2340ed743 Mon Sep 17 00:00:00 2001 From: MillionthOdin16 <102247808+MillionthOdin16@users.noreply.github.com> Date: Wed, 5 Apr 2023 17:44:53 -0400 Subject: [PATCH] Set n_batch to the default value of 8. I think this is leftover from when n_ctx was missing and n_batch was 2048. --- llama_cpp/server/__main__.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama_cpp/server/__main__.py b/llama_cpp/server/__main__.py index 0362cff..67ca115 100644 --- a/llama_cpp/server/__main__.py +++ b/llama_cpp/server/__main__.py @@ -27,7 +27,7 @@ from sse_starlette.sse import EventSourceResponse class Settings(BaseSettings): model: str n_ctx: int = 2048 - n_batch: int = 2048 + n_batch: int = 8 n_threads: int = os.cpu_count() or 1 f16_kv: bool = True use_mlock: bool = True