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

38
llama/llama.cpp/tools/mtmd/clip-impl.h vendored
View File

@@ -39,6 +39,7 @@
#define KEY_FEATURE_LAYER "clip.vision.feature_layer"
#define KEY_PROJ_SCALE_FACTOR "clip.vision.projector.scale_factor"
#define KEY_SPATIAL_MERGE_SIZE "clip.vision.spatial_merge_size"
#define KEY_IS_DEEPSTACK_LAYERS "clip.vision.is_deepstack_layers"
#define KEY_MM_PATCH_MERGE_TYPE "clip.vision.mm_patch_merge_type"
#define KEY_IMAGE_GRID_PINPOINTS "clip.vision.image_grid_pinpoints"
@@ -63,6 +64,7 @@
#define TN_PATCH_EMBD "v.patch_embd.weight" // not rename tensor with ".0" postfix for backwrad compat
#define TN_PATCH_EMBD_1 "v.patch_embd.weight.1"
#define TN_PATCH_BIAS "v.patch_embd.bias"
#define TN_ATTN_QKV "%s.blk.%d.attn_qkv.%s"
#define TN_ATTN_K "%s.blk.%d.attn_k.%s"
#define TN_ATTN_Q "%s.blk.%d.attn_q.%s"
#define TN_ATTN_V "%s.blk.%d.attn_v.%s"
@@ -93,6 +95,9 @@
#define TN_TOK_IMG_BREAK "v.token_embd.img_break" // pixtral
#define TN_TOK_GLM_BOI "adapter.boi" // glm-edge (these embeddings are not in text model)
#define TN_TOK_GLM_EOI "adapter.eoi" // glm-edge (these embeddings are not in text model)
#define TN_DEEPSTACK_NORM "v.deepstack.%d.norm.%s" // qwen3vl deepstack
#define TN_DEEPSTACK_FC1 "v.deepstack.%d.fc1.%s" // qwen3vl deepstack
#define TN_DEEPSTACK_FC2 "v.deepstack.%d.fc2.%s" // qwen3vl deepstack
// mimicpmv
#define TN_MINICPMV_POS_EMBD_K "resampler.pos_embed_k"
@@ -116,6 +121,14 @@
#define TN_MM_NORM_PRE "mm.a.norm_pre.%s"
#define TN_MM_NORM_MID "mm.a.norm_mid.%s"
// cogvlm
#define TN_MM_POST_FC_NORM "mm.post_fc_norm.%s"
#define TN_MM_H_TO_4H "mm.up.%s"
#define TN_MM_GATE "mm.gate.%s"
#define TN_MM_4H_TO_H "mm.down.%s"
#define TN_TOK_BOI "v.boi"
#define TN_TOK_EOI "v.eoi"
// align x to upper multiple of n
#define CLIP_ALIGN(x, n) ((((x) + (n) - 1) / (n)) * (n))
@@ -127,6 +140,7 @@ enum projector_type {
PROJECTOR_TYPE_MINICPMV,
PROJECTOR_TYPE_GLM_EDGE,
PROJECTOR_TYPE_QWEN2VL,
PROJECTOR_TYPE_QWEN3VL,
PROJECTOR_TYPE_GEMMA3,
PROJECTOR_TYPE_IDEFICS3,
PROJECTOR_TYPE_PIXTRAL,
@@ -139,6 +153,9 @@ enum projector_type {
PROJECTOR_TYPE_VOXTRAL,
PROJECTOR_TYPE_LFM2,
PROJECTOR_TYPE_KIMIVL,
PROJECTOR_TYPE_LIGHTONOCR,
PROJECTOR_TYPE_COGVLM,
PROJECTOR_TYPE_JANUS_PRO,
PROJECTOR_TYPE_UNKNOWN,
};
@@ -150,6 +167,7 @@ static std::map<projector_type, std::string> PROJECTOR_TYPE_NAMES = {
{ PROJECTOR_TYPE_GLM_EDGE, "adapter"},
{ PROJECTOR_TYPE_QWEN2VL, "qwen2vl_merger"},
{ PROJECTOR_TYPE_QWEN25VL, "qwen2.5vl_merger"},
{ PROJECTOR_TYPE_QWEN3VL, "qwen3vl_merger"},
{ PROJECTOR_TYPE_GEMMA3, "gemma3"},
{ PROJECTOR_TYPE_IDEFICS3, "idefics3"},
{ PROJECTOR_TYPE_PIXTRAL, "pixtral"},
@@ -161,6 +179,9 @@ static std::map<projector_type, std::string> PROJECTOR_TYPE_NAMES = {
{ PROJECTOR_TYPE_VOXTRAL, "voxtral"},
{ PROJECTOR_TYPE_LFM2, "lfm2"},
{ PROJECTOR_TYPE_KIMIVL, "kimivl"},
{ PROJECTOR_TYPE_LIGHTONOCR,"lightonocr"},
{ PROJECTOR_TYPE_COGVLM, "cogvlm"},
{ PROJECTOR_TYPE_JANUS_PRO, "janus_pro"},
};
static projector_type clip_projector_type_from_string(const std::string & str) {
@@ -203,7 +224,6 @@ static void clip_log_callback_default(enum ggml_log_level level, const char * te
}
struct clip_logger_state {
ggml_log_level verbosity_thold;
ggml_log_callback log_callback;
void * log_callback_user_data;
};
@@ -237,17 +257,11 @@ static void clip_log_internal(enum ggml_log_level level, const char * format, ..
va_end(args);
}
#define LOG_TMPL(level, ...) \
do { \
if ((level) >= g_logger_state.verbosity_thold) { \
clip_log_internal((level), __VA_ARGS__); \
} \
} while (0)
#define LOG_INF(...) LOG_TMPL(GGML_LOG_LEVEL_INFO, __VA_ARGS__)
#define LOG_WRN(...) LOG_TMPL(GGML_LOG_LEVEL_WARN, __VA_ARGS__)
#define LOG_ERR(...) LOG_TMPL(GGML_LOG_LEVEL_ERROR, __VA_ARGS__)
#define LOG_DBG(...) LOG_TMPL(GGML_LOG_LEVEL_DEBUG, __VA_ARGS__)
#define LOG_CNT(...) LOG_TMPL(GGML_LOG_LEVEL_CONT, __VA_ARGS__)
#define LOG_INF(...) clip_log_internal(GGML_LOG_LEVEL_INFO, __VA_ARGS__)
#define LOG_WRN(...) clip_log_internal(GGML_LOG_LEVEL_WARN, __VA_ARGS__)
#define LOG_ERR(...) clip_log_internal(GGML_LOG_LEVEL_ERROR, __VA_ARGS__)
#define LOG_DBG(...) clip_log_internal(GGML_LOG_LEVEL_DEBUG, __VA_ARGS__)
#define LOG_CNT(...) clip_log_internal(GGML_LOG_LEVEL_CONT, __VA_ARGS__)
//
// cpp wrappers