From 8944a1329648c57bb7d66851170938230587a52c Mon Sep 17 00:00:00 2001
From: slaren <2141330+slaren@users.noreply.github.com>
Date: Wed, 19 Apr 2023 11:22:45 +0200
Subject: Add NVIDIA cuBLAS support (#1044)

---
 llama.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'llama.cpp')

diff --git a/llama.cpp b/llama.cpp
index f14324fc..3ff5dc1e 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -1069,7 +1069,7 @@ static bool llama_eval_internal(
     // for big prompts, if BLAS is enabled, it is better to use only one thread
     // otherwise, the threads are spin-lock waiting for the BLAS calls and are degrading the performance
     ggml_cgraph gf = {};
-    gf.n_threads = N >= 32 && ggml_cpu_has_blas() ? 1 : n_threads;
+    gf.n_threads = N >= 32 && ggml_cpu_has_blas() && !ggml_cpu_has_cublas() ? 1 : n_threads;
 
     struct ggml_tensor * embd = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, N);
     memcpy(embd->data, tokens, N*ggml_element_size(embd));
-- 
cgit v1.2.3