From 0ae0946f7a6ed8c477515ba88e53be78066cba5f Mon Sep 17 00:00:00 2001
From: Chandler Swift <chandler@chandlerswift.com>
Date: Thu, 25 Dec 2025 18:16:31 -0600
Subject: [PATCH] oscar: Switch llama-cpp out for Vulkan extensions

This results in a substantial speedup. Before:

    [ Prompt: 2.9 t/s | Generation: 2.5 t/s ]

After (I haven't figured out what the story is with variable speeds,
these are three successive messages of increasing length in the same
conversation):

    [ Prompt: 95.7 t/s | Generation: 11.7 t/s ]
    [ Prompt: 2866.0 t/s | Generation: 13.4 t/s ]
    [ Prompt: 133.1 t/s | Generation: 14.0 t/s ]
    [ Prompt: 188.3 t/s | Generation: 13.6 t/s ]

(benchmarks on Framework 13 AMD 7640U)
---
 oscar/configuration.nix | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/oscar/configuration.nix b/oscar/configuration.nix
index b86f202..aa714fb 100644
--- a/oscar/configuration.nix
+++ b/oscar/configuration.nix
@@ -161,7 +161,7 @@
       wl-clipboard
 
       # ✨ AI ✨
-      llama-cpp
+      llama-cpp-vulkan
 
       # compilers/language utils
       cargo