From: Adrien Gallouët <redacted>
Date: Fri, 10 Apr 2026 15:42:56 +0000 (+0200)
Subject: server : ignore --alias when using --models-preset (#21380)
X-Git-Tag: upstream/0.0.10438~1690
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=5dd102539b97b3cc92c503063a2a244b3c7d57bd;p=pkg%2Fggml%2Fsources%2Fllama.cpp

server : ignore --alias when using --models-preset (#21380)

I'm not sure what the purpose of keeping `--alias` was when using
`--models-preset`, but the result is really weird, as shown in the
following logs:

    $ build/bin/llama-server --models-preset preset.ini --alias "Gemma 4 E4B UD Q8_K_XL"
    ...
    init: using 31 threads for HTTP server
    srv   load_models: Loaded 2 cached model presets
    srv   load_models: Loaded 1 custom model presets from preset.ini
    main: failed to initialize router models: alias 'Gemma 4 E4B UD Q8_K_XL' for model 'angt/test-split-model-stories260K:F32' conflicts with existing model name

So I propose to simply ignore `--alias` too in this case. With this
commit, the server starts in routing mode correctly.

Signed-off-by: Adrien Gallouët <redacted>
---

diff --git a/tools/server/server-models.cpp b/tools/server/server-models.cpp
index c83709272..c4ef62d2e 100644
--- a/tools/server/server-models.cpp
+++ b/tools/server/server-models.cpp
@@ -98,6 +98,7 @@ static void unset_reserved_args(common_preset & preset, bool unset_model_args) {
     if (unset_model_args) {
         preset.unset_option("LLAMA_ARG_MODEL");
         preset.unset_option("LLAMA_ARG_MMPROJ");
+        preset.unset_option("LLAMA_ARG_ALIAS");
         preset.unset_option("LLAMA_ARG_HF_REPO");
     }
 }