fix(kimi-k3): raise LLAMA_MAX_EXPERTS to 1024 for K3's 896 experts

Mirrors upstream PR 26185 commit cf11c4c. Without this the real
checkpoint fails the n_expert assert at load; the synthetic test model
(8 experts) never hit it.

Author: worthant

src/llama-hparams.h

@@ -7,7 +7,7 @@
 
 // bump if necessary
 #define LLAMA_MAX_LAYERS  512
-#define LLAMA_MAX_EXPERTS 512 // Qwen3 Next
+#define LLAMA_MAX_EXPERTS 1024 // Kimi K3 has 896 experts
 
 enum llama_expert_gating_func_type {
     LLAMA_EXPERT_GATING_FUNC_TYPE_NONE           = 0,