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

14
llama/llama.cpp/tools/mtmd/mtmd.h vendored
View File

@@ -82,9 +82,13 @@ struct mtmd_context_params {
bool use_gpu;
bool print_timings;
int n_threads;
enum ggml_log_level verbosity;
const char * image_marker; // deprecated, use media_marker instead
const char * media_marker;
enum llama_flash_attn_type flash_attn_type;
// limit number of image tokens, only for vision models with dynamic resolution
int image_min_tokens; // minimum number of tokens for image input (default: read from metadata)
int image_max_tokens; // maximum number of tokens for image input (default: read from metadata)
};
MTMD_API const char * mtmd_default_marker(void);
@@ -156,7 +160,7 @@ MTMD_API const mtmd_image_tokens * mtmd_input_chunk_get_tokens_image(const mtmd
MTMD_API size_t mtmd_input_chunk_get_n_tokens (const mtmd_input_chunk * chunk);
// returns nullptr for ID on text chunk
MTMD_API const char * mtmd_input_chunk_get_id (const mtmd_input_chunk * chunk);
// number of temporal positions (always 1 for M-RoPE, n_tokens otherwise)
// number of temporal positions (equals to max(t,h,w) for M-RoPE; equals to n_tokens otherwise)
MTMD_API llama_pos mtmd_input_chunk_get_n_pos (const mtmd_input_chunk * chunk);
// in case you want to use custom logic to handle the chunk (i.e. KV cache management)
@@ -174,7 +178,7 @@ MTMD_API size_t mtmd_image_tokens_get_n_tokens(const mtmd_image_tokens * i
MTMD_API size_t mtmd_image_tokens_get_nx (const mtmd_image_tokens * image_tokens);
MTMD_API size_t mtmd_image_tokens_get_ny (const mtmd_image_tokens * image_tokens);
MTMD_API const char * mtmd_image_tokens_get_id (const mtmd_image_tokens * image_tokens); // TODO: deprecate
// number of temporal positions (always 1 for M-RoPE, n_tokens otherwise)
// number of temporal positions (equals to max(t,h,w) for M-RoPE; equals to n_tokens otherwise)
MTMD_API llama_pos mtmd_image_tokens_get_n_pos (const mtmd_image_tokens * image_tokens); // TODO: deprecate
// tokenize an input text prompt and a list of bitmaps (images/audio)
@@ -213,6 +217,10 @@ MTMD_API int32_t mtmd_encode_chunk(mtmd_context * ctx,
// llama_model_n_embd(model) * mtmd_input_chunk_get_n_tokens(chunk) * sizeof(float)
MTMD_API float * mtmd_get_output_embd(mtmd_context * ctx);
// Set callback for all future logging events.
// If this is not called, or NULL is supplied, everything is output on stderr.
MTMD_API void mtmd_log_set(ggml_log_callback log_callback, void * user_data);
/////////////////////////////////////////
// test function, to be used in test-mtmd-c-api.c