llama: update to commit 71e90e88 (#10192)

llama/patches/0019-fix-compiler-error-in-clip.h.patch

@@ -0,0 +1,39 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: jmorganca <jmorganca@gmail.com>
+Date: Tue, 8 Apr 2025 20:49:50 -0700
+Subject: [PATCH] fix compiler error in clip.h
+
+fixes an error that occurs in clip.h when compiling
+using CGo
+---
+ examples/llava/clip.h | 5 +++--
+ 1 file changed, 3 insertions(+), 2 deletions(-)
+
+diff --git a/examples/llava/clip.h b/examples/llava/clip.h
+index cc133a58..5fc45d3e 100644
+--- a/examples/llava/clip.h
++++ b/examples/llava/clip.h
+@@ -30,12 +30,13 @@ struct clip_image_size {
+     int height;
+ };
+ 
++struct clip_image_f32;
+ struct clip_image_u8_batch;
+ struct clip_image_f32_batch;
+ 
+ struct clip_context_params {
+     bool use_gpu;
+-    ggml_log_level verbosity;
++    enum ggml_log_level verbosity;
+ };
+ 
+ // deprecated, use clip_init
+@@ -84,7 +85,7 @@ CLIP_API void clip_image_f32_batch_free(struct clip_image_f32_batch * batch);
+ CLIP_API size_t clip_image_f32_batch_n_images(const struct clip_image_f32_batch * batch); // equivalent to batch->size()
+ CLIP_API size_t clip_image_f32_batch_nx(const struct clip_image_f32_batch * batch, int idx); // equivalent to batch[idx]->nx
+ CLIP_API size_t clip_image_f32_batch_ny(const struct clip_image_f32_batch * batch, int idx); // equivalent to batch[idx]->ny
+-CLIP_API clip_image_f32 * clip_image_f32_get_img(const struct clip_image_f32_batch * batch, int idx); // equivalent to batch[idx]->data
++CLIP_API struct clip_image_f32 * clip_image_f32_get_img(const struct clip_image_f32_batch * batch, int idx); // equivalent to batch[idx]->data
+ 
+ /**
+  * Build image from pixels decoded by other libraries instead of stb_image.h for better performance.