model : support for DeepseekV32ForCausalLM with generic DeepSeek Sparse Attention...

model : support for DeepseekV32ForCausalLM with generic DeepSeek Sparse Attention (DSA) implementation (llama/23346)

* llama : support DeepSeek V3.2 model family (with DSA lightning indexer)

* convert : handle DeepseekV32ForCausalLM architecture

* ggml : support for f16 GGML_OP_FILL

* memory : separate hparams argument in llama_kv_cache constructor

* memory : add llama_kv_cache_dsa memory (KV cache + lightning indexer cache)

* llama : support for LLM_ARCH_DEEPSEEK32

* model : llama_model_deepseek32 implementation

* model : merge two scale operations into one in DSA lightning indexer implementation

* chore : remove unused code

* model : support NVFP4 in DeepSeek V3.2

Co-authored-by: Sigbjørn Skjæret <redacted>
* memory : refactoring TODO

Co-authored-by: ggerganov <redacted>
---------

Co-authored-by: Stanisław Szymczyk <redacted>
Co-authored-by: Sigbjørn Skjæret <redacted>
Co-authored-by: ggerganov <redacted>