diff --git a/tools/server/README.md b/tools/server/README.md
index 6828ef7382..8fd478eb32 100644
--- a/tools/server/README.md
+++ b/tools/server/README.md
@@ -512,7 +512,7 @@ These words will not be included in the completion, so make sure to add them to
 
 `timings_per_token`: Include prompt processing and text generation speed information in each response.  Default: `false`
 
-`return_progress`: Include prompt processing progress in `stream` mode. The progress will be contained inside `prompt_progress` with 3 values: `total`, `cache` and `processed`. The overall progress is `processed/total`, while the actual timed progress is `(processed-cache)/(total-cache)`. Default: `false`
+`return_progress`: Include prompt processing progress in `stream` mode. The progress will be contained inside `prompt_progress` with 4 values: `total`, `cache`, `processed`, and `time_ms`. The overall progress is `processed/total`, while the actual timed progress is `(processed-cache)/(total-cache)`. The `time_ms` field contains the elapsed time in milliseconds since prompt processing started. Default: `false`
 
 `post_sampling_probs`: Returns the probabilities of top `n_probs` tokens after applying sampling chain.
 
diff --git a/tools/server/server.cpp b/tools/server/server.cpp
index 164e8cf4e7..9d91e32d1f 100644
--- a/tools/server/server.cpp
+++ b/tools/server/server.cpp
@@ -3078,7 +3078,7 @@ struct server_context {
             res->progress.total     = slot.task->n_tokens();
             res->progress.cache     = slot.n_prompt_tokens_cache;
             res->progress.processed = slot.prompt.tokens.size();
-            res->progress.time_ms   = (ggml_time_us() - slot.t_start_process_prompt / 1000);
+            res->progress.time_ms   = (ggml_time_us() - slot.t_start_process_prompt) / 1000;
         } else {
             res->content = tkn.text_to_send;
             res->tokens  = { tkn.tok };