From ce2c7d72e2d06988b5ddec6811ab923254542077 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Sun, 18 Jun 2023 09:09:47 +0300 Subject: metal : handle buffers larger than device's maxBufferLength (#1826) * metal : handle buffers larger than device's maxBufferLength * metal : print more verbose device info + handle errors * metal : fix prints for overlapping views * metal : minimize view overlap to try to utilize device memory better --- ggml.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'ggml.h') diff --git a/ggml.h b/ggml.h index 9b0c846..1380c53 100644 --- a/ggml.h +++ b/ggml.h @@ -500,8 +500,9 @@ extern "C" { GGML_API size_t ggml_set_scratch (struct ggml_context * ctx, struct ggml_scratch scratch); GGML_API void ggml_set_no_alloc(struct ggml_context * ctx, bool no_alloc); - GGML_API void * ggml_get_mem_buffer(struct ggml_context * ctx); - GGML_API size_t ggml_get_mem_size (struct ggml_context * ctx); + GGML_API void * ggml_get_mem_buffer (const struct ggml_context * ctx); + GGML_API size_t ggml_get_mem_size (const struct ggml_context * ctx); + GGML_API size_t ggml_get_max_tensor_size(const struct ggml_context * ctx); GGML_API struct ggml_tensor * ggml_new_tensor( struct ggml_context * ctx, -- cgit v1.2.3