common : enable default speculative config

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp

docs/preset.md

@@ -26,7 +26,7 @@ ctx-size             = 0
 mmap                 = 1
 kv-unified           = 1
 parallel             = 4
-spec-default         = 1
+no-spec-type         = ngram-mod
 
 [Qwen3.5-4B]
 hf                   = unsloth/Qwen3.5-4B-GGUF:Q4_K_M
@@ -52,6 +52,9 @@ chat-template-kwargs = {"reasoning_effort": "high"}
 
 The preset will be loaded similarly to the `--models-preset` option. Therefore, you can also override certain params via CLI arguments:
 
+> [!NOTE]
+> A default speculative decoding is enabled by default for the server and CLI.
+
 ```sh
 # Force temp = 0.1, overriding the preset value
 llama-cli -hf username/my-preset --temp 0.1

docs/speculative.md

@@ -226,10 +226,12 @@ Use exactly one of these options:
 ```
 --spec-type [none|draft-simple|draft-eagle3|draft-dflash|draft-dspark|draft-mtp|ngram-cache|ngram-simple|ngram-map-k|ngram-map-k4v|ngram-mod]
                                         comma-separated list of types of speculative decoding to use
-                                        (default: none)
+                                        (default: server/CLI default config, none for other tools)
                                         (env: LLAMA_ARG_SPEC_TYPE)
---spec-default                          use default speculative decoding config
-                                        (enables ngram-mod)
+--no-spec-type [none|draft-simple|draft-eagle3|draft-dflash|draft-dspark|draft-mtp|ngram-cache|ngram-simple|ngram-map-k|ngram-map-k4v|ngram-mod]
+                                        comma-separated list of types of speculative decoding to remove
+                                        (env: LLAMA_ARG_NO_SPEC_TYPE)
+--spec-default                          DEPRECATED: default speculative decoding is enabled by default
 ```
 
 ### Draft Model Parameters