llama : document that only one on-device state can be saved per sequence (#23520)

diff --git a/include/llama.h b/include/llama.h
index 75095b22d08f8813b8f3e37de48e6a340cc0716c..e8374c53b706189849cfc310c271be2cabe783a0 100644 (file)
--- a/include/llama.h
+++ b/include/llama.h
@@ -874,7 +874,8 @@ extern "C" {
 // work only with partial states, such as SWA KV cache or recurrent cache (e.g. Mamba)
 #define LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY 1
 
-// keeps the tensor data on device buffers (i.e. not accessible in host memory, but faster save/load)
+// Keeps the tensor data on device buffers (i.e. not accessible in host memory, but faster save/load).
+// Getting the state for a seq_id with this flag invalidates all prior states gotten for that seq_id with this flag.
 #define LLAMA_STATE_SEQ_FLAGS_ON_DEVICE 2
 
     typedef uint32_t llama_state_seq_flags;