server: id_slot pinned to an empty slot skips the prompt cache #34

Upstream: ggml-org#28139

Pinning a request to an empty slot bypasses an exact prompt-cache match and reprocesses the entire prompt.

Environment: current main 465e49b9, Linux aarch64, Gemma 4 12B Q4_K_M, --parallel 2 --slots --cache-ram 4096.

Reproduction:

1. Send prompt A with cache_prompt:true,id_slot:0.
2. Send prompt B with the same options, moving A to the prompt cache.
3. Send A with cache_prompt:true,id_slot:1.

Observed on step 3: cache_n:0, prompt_n:290.

For an empty pinned slot, f_keep = 0 / 0 becomes NaN, so f_keep < 0.5f is false and the cache is not loaded. The host-memory prompt-cache path dates to d00cbea6.