mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
mtmd : support Kimi VL model (#15458)
* convert : fix tensor naming conflict for llama 4 vision * convert ok * support kimi vision model * clean up * fix style * fix calc number of output tokens * refactor resize_position_embeddings * add test case * rename build fn * correct a small bug
This commit is contained in:
@@ -135,6 +135,7 @@ enum projector_type {
|
||||
PROJECTOR_TYPE_QWEN25O, // will be replaced by QWEN2A or QWEN25VL depending on clip_ctx
|
||||
PROJECTOR_TYPE_VOXTRAL,
|
||||
PROJECTOR_TYPE_LFM2,
|
||||
PROJECTOR_TYPE_KIMIVL,
|
||||
PROJECTOR_TYPE_UNKNOWN,
|
||||
};
|
||||
|
||||
@@ -156,6 +157,7 @@ static std::map<projector_type, std::string> PROJECTOR_TYPE_NAMES = {
|
||||
{ PROJECTOR_TYPE_QWEN25O, "qwen2.5o"},
|
||||
{ PROJECTOR_TYPE_VOXTRAL, "voxtral"},
|
||||
{ PROJECTOR_TYPE_LFM2, "lfm2"},
|
||||
{ PROJECTOR_TYPE_KIMIVL, "kimivl"},
|
||||
};
|
||||
|
||||
static projector_type clip_projector_type_from_string(const std::string & str) {
|
||||
|
||||
Reference in New Issue
Block a user