From 315102f89109f1b67c8f89f12d98ab646685e333 Mon Sep 17 00:00:00 2001
From: Jared Van Bortel <jared@nomic.ai>
Date: Mon, 5 Feb 2024 16:02:01 -0500
Subject: [PATCH] kompute : disable GPU offload for Mixtral

We haven't implemented the necessary GPU kernels yet.

Fixes this crash:

ggml_vk_graph_compute: error: unsupported op 'ARGSORT'
GGML_ASSERT: /home/jared/src/forks/gpt4all/gpt4all-backend/llama.cpp-mainline/ggml-kompute.cpp:1508: !"unsupported op"

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
---
 llama.cpp | 1 +
 1 file changed, 1 insertion(+)

diff --git a/llama.cpp b/llama.cpp
index 21fa02b8bc91e..5260f07d4bf22 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -4138,6 +4138,7 @@ static int llama_model_load(const std::string & fname, llama_model & model, llam
 #ifdef GGML_USE_KOMPUTE
         if (params.n_gpu_layers > 0 && (
             !(model.arch == LLM_ARCH_LLAMA || model.arch == LLM_ARCH_FALCON)
+            || model.hparams.n_expert > 0
             || !(
                 model.ftype == LLAMA_FTYPE_ALL_F32 ||
                 model.ftype == LLAMA_FTYPE_MOSTLY_F16 ||