llama : MTP clean-up (#23269)

* llama : disable equal splits for recurrent memory with partial rollback

* spec : re-enable p-min with MTP drafts

* spec : re-enable ngram spec in combination with RS rollback

* spec : fix ngram-map-* params

* spec : fix acceptance logic in combined ngram + draft configs

* graph : fix reuse for combined `token` + `embd` batches

* spec : log parameters for each speculative implementation

- add LOG_INF in each constructor with implementation type and parameters
- extract device string logic into common_speculative_get_devices_str()
- move 'adding speculative implementation' log from init into constructors

Assisted-by: llama.cpp:local pi

* spec : extend --spec-default with ngram-map-k4v

Assisted-by: llama.cpp:local pi

* minor : fix n_embd log

* args : update draft.n_max == 3 + regen docs

* spec : relax ngram-mod rejection thold to 0.25 @ 5 low

* logs : improve

* docs : update speculative decoding CLI argument documentation

- Add missing draft model CPU scheduling and tensor override parameters
- Update --spec-type to include all available types (excluding draft-eagle3 WIP)
- Fix default values to match implementation (n_max=3, n_min=0, p_min=0.0)
- Remove deprecated options (spec-draft-ctx-size, spec-draft-replace)
- Add environment variables for new parameters

Assisted-by: llama.cpp:local pi

* arg : step-back on adding k4v to the default spec config

* cont : fix name

src/llama-graph.h

@@ -581,7 +581,8 @@ struct llm_graph_params {
             ubatch.n_seqs_unq   == other.ubatch.n_seqs_unq &&
             (
                 (!ubatch.token && !other.ubatch.token) ||
-                (!ubatch.embd  && !other.ubatch.embd)
+                (!ubatch.embd  && !other.ubatch.embd)  ||
+                (ubatch.token && other.ubatch.token && ubatch.embd && other.ubatch.embd)
             );
 
         // when we split the batch using "equal_seqs" we have to verify that the participating sequences are the same