From: Georgi Gerganov <redacted>
Date: Fri, 2 May 2025 06:48:31 +0000 (+0300)
Subject: server : add cache reuse card link to help (#13230)
X-Git-Tag: upstream/0.0.5318~61
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=fab647e8842c5f80da7e8f2c625dab6a0e19e5d4;p=pkg%2Fggml%2Fsources%2Fllama.cpp

server : add cache reuse card link to help (#13230)

* server : add cache reuse card link to help

* args : use short url
---

diff --git a/common/arg.cpp b/common/arg.cpp
index e35417de..aface844 100644
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -2783,7 +2783,10 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_THREADS_HTTP"));
     add_opt(common_arg(
         {"--cache-reuse"}, "N",
-        string_format("min chunk size to attempt reusing from the cache via KV shifting (default: %d)", params.n_cache_reuse),
+        string_format(
+            "min chunk size to attempt reusing from the cache via KV shifting (default: %d)\n"
+            "[(card)](https://ggml.ai/f0.png)", params.n_cache_reuse
+        ),
         [](common_params & params, int value) {
             params.n_cache_reuse = value;
         }
diff --git a/examples/server/README.md b/examples/server/README.md
index a2a09032..61446a0b 100644
--- a/examples/server/README.md
+++ b/examples/server/README.md
@@ -154,7 +154,7 @@ The project is under active development, and we are [looking for feedback and co
 | `--ssl-cert-file FNAME` | path to file a PEM-encoded SSL certificate<br/>(env: LLAMA_ARG_SSL_CERT_FILE) |
 | `-to, --timeout N` | server read/write timeout in seconds (default: 600)<br/>(env: LLAMA_ARG_TIMEOUT) |
 | `--threads-http N` | number of threads used to process HTTP requests (default: -1)<br/>(env: LLAMA_ARG_THREADS_HTTP) |
-| `--cache-reuse N` | min chunk size to attempt reusing from the cache via KV shifting (default: 0)<br/>(env: LLAMA_ARG_CACHE_REUSE) |
+| `--cache-reuse N` | min chunk size to attempt reusing from the cache via KV shifting (default: 0)<br/>[(card)](https://ggml.ai/f0.png)<br/>(env: LLAMA_ARG_CACHE_REUSE) |
 | `--metrics` | enable prometheus compatible metrics endpoint (default: disabled)<br/>(env: LLAMA_ARG_ENDPOINT_METRICS) |
 | `--slots` | enable slots monitoring endpoint (default: disabled)<br/>(env: LLAMA_ARG_ENDPOINT_SLOTS) |
 | `--props` | enable changing global properties via POST /props (default: disabled)<br/>(env: LLAMA_ARG_ENDPOINT_PROPS) |