Merge ffn_up and ffn_gate experts tensors (#1137)

* WIP - not working

* WIP - not working

* WIP - GPT-OSS working

However, extremely stupid. The only way I could correctly repack the
up/gate experts is to copy up and gate into host buffers, repack
into another host buffer, copy back into the ffn_up_gate_exps tensor.
This is going to be very slow for giant 500 GB models.

My attempts to do this via a compute graph on the backend holding
the tensors was unsuccessful.

For GPT-OSS-20B I see ~6-7% better PP when using the original
ik_llama.cpp fused_up_gate CUDA implementation, and ~10% when
using the small batch size implementation.

Other models are not working yet on CUDA as I need to fix the
fused mul-unary implementation.

* WIP

* WIP - Qwen3-MoE (and hopefully all others) working

But when I say here and in the previous commit "working",
I mean PP is working. TG is still broken.

* WIP: TG seems to be working

* Minor

* Add command line option to merge experts up/gate

* Add merge up/gate command line parameter to llama-bench

* Turn off merge_up_gate_exps if split mode graph

It is not yet implemented

* When no bias, allow merging up/gate with tensor overrides

* Arghh, we need to increase the context size again

* Cleanup

include/llama.h

@@ -392,6 +392,7 @@ extern "C" {
         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
+        bool merge_up_gate_exps;  // if true, merge ffn_up_exps and ffn_gate_exps 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