mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-21 22:33:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml update to b7108 (#12992)

Browse Source 
* Revert "vulkan: temporary cary of vulkan fixes (#12971)"

This reverts commit 3a9e8e9fd4.

* ggml update to b7087

* fix argsort on metal

* update to b7108

* fix bakllava regression

This model lacks the metadata for the projector type.

* update to b7209

* fix TopK perf

* only build arm code on arm
This commit is contained in:
Daniel Hiltgen
2025-12-03 19:43:29 -08:00
committed by GitHub
parent 854d40edc5
commit 0cf7794b16
303 changed files with 32711 additions and 23435 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
llama/llama.cpp/tools/mtmd/clip.h vendored
View File

@@ -1,6 +1,7 @@
#pragma once
#include "ggml.h"
#include <stddef.h>
#include <stdint.h>
@@ -22,9 +23,17 @@ enum clip_modality {
CLIP_MODALITY_AUDIO,
};
enum clip_flash_attn_type {
CLIP_FLASH_ATTN_TYPE_AUTO = -1,
CLIP_FLASH_ATTN_TYPE_DISABLED = 0,
CLIP_FLASH_ATTN_TYPE_ENABLED = 1,
};
struct clip_context_params {
bool use_gpu;
enum ggml_log_level verbosity;
enum clip_flash_attn_type flash_attn_type;
int image_min_tokens;
int image_max_tokens;
};
struct clip_init_result {