Merge Q, K, V (#878)

* POC: merge Q, K, V into a single, contiguous tensor

Done just for Qwen3-MoE, where I see a 4% uplift in TG.
PP performance gain is sub-percent, if any.
Still, it seems it makes sense to do it in general given
the TG performance gain.

* WIP

* merge_qkv: it works for gpt-oss

...but we see a smaller TG gain (~1.5%)

* WIP

* Don't ignore the return value of create_tensors()

else, when q, k, v get merged and we are running on the CPU,
we get a crash because the backend is trying to use mmap,
but that no longer works.

* merge_qkv: bias can be required, optional, or mandatory

* merge_qkv: glm4.5moe

* merge_qkv: add command loine argument to enable

* merge_qkv: fix tensor dimensions

* merge_qkv: llama-4

* merge_qkv: qwen3 (dense)

* merge_qkv: simplify build_qwen3moe

* cohere2 - simplify graph building

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

include/llama.h

@@ -382,6 +382,7 @@ extern "C" {
         bool repack_tensors;// repack if available
         bool use_thp;       // use transparent huge pages (linux only)
         bool validate_quants; // if true, check for NaNs while loading the model
+        bool merge_qkv;     // if true, merge separate Q, K, V tensors into a single, contiguous tensor
     };
 
     // NOTE: changing the default values of parameters marked as [EXPERIMENTAL] may cause crashes or incorrect results in certain configurations