Port of Qwen3-VL support from mainline (#883)

* Port of Qwen3-VL for latest ik_llama.cpp

- convert_hf_to_gguf.py - Not touched, use llama.cpp to convert model instead
- sysl and metal support for imrope not added
- Vulkan support for imrope not tested
- Code not tested

* Bugfix n_embd was declared multiple times

https://github.com/ikawrakow/ik_llama.cpp/pull/883#issuecomment-3471179655

* Fix n_embd issue with qwen3vl

* model.output tensor not required

https://github.com/ikawrakow/ik_llama.cpp/pull/883#discussion_r2480388389

* Improved logic for qkv combined tensors

59ceaf8fcb (r2480395800)
59ceaf8fcb (r2480398187)

* Fix n_embd for merge_qkv() + cleaner code

https://github.com/ikawrakow/ik_llama.cpp/pull/883#discussion_r2481227395

* Revert TENSOR_NOT_REQUIRED
This commit is contained in:
Thireus ☠
2025-11-04 17:20:54 +00:00
committed by GitHub
parent 7e956a32ce
commit 5536e99d42
21 changed files with 850 additions and 78 deletions

View File

@@ -122,6 +122,7 @@ extern "C" {
LLAMA_ROPE_TYPE_NORM = 0,
LLAMA_ROPE_TYPE_NEOX = GGML_ROPE_TYPE_NEOX,
LLAMA_ROPE_TYPE_MROPE = GGML_ROPE_TYPE_MROPE,
LLAMA_ROPE_TYPE_IMROPE = GGML_ROPE_TYPE_IMROPE,
LLAMA_ROPE_TYPE_VISION = GGML_ROPE_TYPE_VISION,
};