Update llama.cpp to b10930 and migrate model loading option

2026-09-12 20:41:05 +02:00
parent 6c00b00add
commit 2415b27160
9 changed files with 122 additions and 28 deletions
@@ -129,7 +129,8 @@ services:
      - "off"
      - --n-gpu-layers
      - all
-      - --no-mmap
+      - --load-mode
+      - none
      - --no-ui
      - --temperature
      - "0.2"
@@ -206,7 +207,8 @@ services:
      - "off"
      - --n-gpu-layers
      - all
-      - --no-mmap
+      - --load-mode
+      - none
      - --no-ui
      - --temperature
      # Qwen3.8's official thinking-mode sampler. The former 0.2 setting was
@@ -292,7 +294,8 @@ services:
      - "off"
      - --n-gpu-layers
      - all
-      - --no-mmap
+      - --load-mode
+      - none
      - --no-ui
      - --temperature
      - "1.0"
@@ -371,7 +374,8 @@ services:
      - "off"
      - --n-gpu-layers
      - all
-      - --no-mmap
+      - --load-mode
+      - none
      - --no-ui
      - --temperature
      - "0.2"
@@ -449,7 +453,8 @@ services:
      - "off"
      - --n-gpu-layers
      - all
-      - --no-mmap
+      - --load-mode
+      - none
      - --no-ui
      - --temperature
      - "0.2"
@@ -531,7 +536,8 @@ services:
      - "off"
      - --n-gpu-layers
      - all
-      - --no-mmap
+      - --load-mode
+      - none
      - --no-ui
      - --temperature
      - "0.2"