context : reserve new scheduler when graph topology changes (#18547)

* context : reserve new scheduler when graph topology changes

* cont : fix

* cont : fix reserve

* cont : reserve only when changes occur + timing

* context : add comments

* llama : reserve on sampler changes

* common : allow null common_sampler

* server : task declares needs (embd, logits, sampling)

* server : do not init sampler if not needed

* llama : fix need_reserve when unsetting a sampler

* server : consolidate slot reset/clear logic

src/llama-cparams.h

@@ -30,10 +30,12 @@ struct llama_cparams {
     bool causal_attn;
     bool offload_kqv;
     bool flash_attn;
+    bool auto_fa;
     bool no_perf;
     bool warmup;
     bool op_offload;
     bool kv_unified;
+    bool pipeline_parallel;
 
     enum llama_pooling_type pooling_type;