server : do not clear slots without unified KV cache (#24190)

* Always export idle slots to RAM

Without this, a slot's VRAM cache may not be written to RAM.  If this
slot happens to be busy then later on, this triggers needless
preprocessing in another slot.

* cont : clean-up

---------

Co-authored-by: Christoph Weiss <weiss@wsoptics.de>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

tools/server/README.md

@@ -165,7 +165,7 @@ For the full list of features, please refer to [server's changelog](https://gith
 | `-cms, --checkpoint-min-step N` | minimum spacing between context checkpoints in tokens (default: 256, 0 = no minimum)<br/>(env: LLAMA_ARG_CHECKPOINT_MIN_SPACING_NT) |
 | `-cram, --cache-ram N` | set the maximum cache size in MiB (default: 8192, -1 - no limit, 0 - disable)[(more info)](https://github.com/ggml-org/llama.cpp/pull/16391)<br/>(env: LLAMA_ARG_CACHE_RAM) |
 | `-kvu, --kv-unified, -no-kvu, --no-kv-unified` | use single unified KV buffer shared across all sequences (default: enabled if number of slots is auto)<br/>(env: LLAMA_ARG_KV_UNIFIED) |
-| `--cache-idle-slots, --no-cache-idle-slots` | save and clear idle slots on new task (default: enabled, requires unified KV and cache-ram)<br/>(env: LLAMA_ARG_CACHE_IDLE_SLOTS) |
+| `--cache-idle-slots, --no-cache-idle-slots` | save idle slots to the prompt cache on new task, and clear them when using unified KV (default: enabled, requires cache-ram)<br/>(env: LLAMA_ARG_CACHE_IDLE_SLOTS) |
 | `--context-shift, --no-context-shift` | whether to use context shift on infinite text generation (default: disabled)<br/>(env: LLAMA_ARG_CONTEXT_SHIFT) |
 | `-r, --reverse-prompt PROMPT` | halt generation at PROMPT, return control in interactive mode |
 | `-sp, --special` | special tokens output enabled (default: false) |