From c88dd2899ae1248065d704c6ef9744a3742a0af7 Mon Sep 17 00:00:00 2001
From: Lumpiasty <arek.dzski@gmail.com>
Date: Tue, 10 Mar 2026 13:47:56 +0100
Subject: [PATCH] remove ttl of all models in llama-swap

---
 apps/llama/configs/config.yaml | 21 ---------------------
 1 file changed, 21 deletions(-)

diff --git a/apps/llama/configs/config.yaml b/apps/llama/configs/config.yaml
index 8309c4d..1f29f3b 100644
--- a/apps/llama/configs/config.yaml
+++ b/apps/llama/configs/config.yaml
@@ -35,7 +35,6 @@ groups:
 
 models:
   "gemma3-12b":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/gemma-3-12b-it-GGUF:Q4_K_M
@@ -43,7 +42,6 @@ models:
         ${common_args}
 
   "gemma3-12b-novision":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/gemma-3-12b-it-GGUF:Q4_K_M
@@ -52,7 +50,6 @@ models:
         ${common_args}
 
   "gemma3-4b":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/gemma-3-4b-it-GGUF:Q4_K_M
@@ -60,7 +57,6 @@ models:
         ${common_args}
 
   "gemma3-4b-novision":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/gemma-3-4b-it-GGUF:Q4_K_M
@@ -69,7 +65,6 @@ models:
         ${common_args}
 
   "Qwen3-Coder-Next-GGUF:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3-Coder-Next-GGUF:Q4_K_M
@@ -83,7 +78,6 @@ models:
         ${common_args}
 
   "Qwen3.5-35B-A3B-GGUF:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M
@@ -91,7 +85,6 @@ models:
         ${common_args}
 
   "Qwen3.5-35B-A3B-GGUF-nothink:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M
@@ -102,7 +95,6 @@ models:
   # The "heretic" version does not provide the mmproj
   # so providing url to the one from the non-heretic version.
   "Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf mradermacher/Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M
@@ -111,7 +103,6 @@ models:
         ${common_args}
 
   "Qwen3.5-35B-A3B-heretic-GGUF-nothink:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf mradermacher/Qwen3.5-35B-A3B-heretic-GGUF:Q4_K_M
@@ -121,7 +112,6 @@ models:
         ${thinking_off}
 
   "Qwen3.5-0.8B-GGUF:Q4_K_XL":
-    ttl: 0
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-0.8B-GGUF:Q4_K_XL
@@ -130,7 +120,6 @@ models:
         ${thinking_on}
 
   "Qwen3.5-0.8B-GGUF-nothink:Q4_K_XL":
-    ttl: 0
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-0.8B-GGUF:Q4_K_XL
@@ -140,7 +129,6 @@ models:
         ${thinking_off}
 
   "Qwen3.5-2B-GGUF:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-2B-GGUF:Q4_K_M
@@ -149,7 +137,6 @@ models:
         ${thinking_on}
 
   "Qwen3.5-2B-GGUF-nothink:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-2B-GGUF:Q4_K_M
@@ -158,7 +145,6 @@ models:
         ${thinking_off}
 
   "Qwen3.5-4B-GGUF:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-4B-GGUF:Q4_K_M
@@ -167,7 +153,6 @@ models:
         ${thinking_on}
 
   "Qwen3.5-4B-GGUF-nothink:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-4B-GGUF:Q4_K_M
@@ -176,7 +161,6 @@ models:
         ${thinking_off}
 
   "Qwen3.5-4B-heretic-GGUF:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf mradermacher/Qwen3.5-4B-heretic-GGUF:Q4_K_M
@@ -186,7 +170,6 @@ models:
         ${thinking_on}
 
   "Qwen3.5-4B-heretic-GGUF-nothink:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf mradermacher/Qwen3.5-4B-heretic-GGUF:Q4_K_M
@@ -196,7 +179,6 @@ models:
         ${thinking_off}
 
   "Qwen3.5-9B-GGUF:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-9B-GGUF:Q4_K_M
@@ -205,7 +187,6 @@ models:
         ${thinking_on}
 
   "Qwen3.5-9B-GGUF-nothink:Q4_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-9B-GGUF:Q4_K_M
@@ -214,7 +195,6 @@ models:
         ${thinking_off}
 
   "Qwen3.5-9B-GGUF:Q3_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-9B-GGUF:Q3_K_M
@@ -223,7 +203,6 @@ models:
         ${thinking_on}
 
   "Qwen3.5-9B-GGUF-nothink:Q3_K_M":
-    ttl: 600
     cmd: |
       /app/llama-server
         -hf unsloth/Qwen3.5-9B-GGUF:Q3_K_M