From c4a1e1d108d9a1eb1a199b8c993f61f7bb4d5160 Mon Sep 17 00:00:00 2001 From: John Mai Date: Thu, 7 Mar 2024 00:42:08 +0800 Subject: [PATCH] fix: typo (#16) --- Tools/llm-tool/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Tools/llm-tool/README.md b/Tools/llm-tool/README.md index 259c6f0..5b23d8f 100644 --- a/Tools/llm-tool/README.md +++ b/Tools/llm-tool/README.md @@ -52,7 +52,7 @@ There are a couple options: - build Release - force the model evaluation to run on the main thread, e.g. using @MainActor -- build `Cmlx` with optimizations by modifying `mlx/Package.swift` and adding `.unsafeOptions(["-O3"]),` around line 87 +- build `Cmlx` with optimizations by modifying `mlx/Package.swift` and adding `.unsafeFlags(["-O"]),` around line 87 Building in Release / optimizations will remove a lot of tail calls in the C++ layer. These lead to the stack overflows.