feat(llama-swap): add 128k max-ctx profiles for qwen3.5 variants

Replace verbose Hugging Face model references with concise local aliases for
Qwen3.5 models to improve readability and maintainability.

ai/docker-compose.yml

@@ -8,7 +8,9 @@ services:
       - "/srv/docker/ai/data/data:/app/backend/data" # Double data is intentional
       - "/srv/docker/ai/data/.webui_secret_key:/app/backend/.webui_secret_key"
     environment:
-      - OLLAMA_BASE_URL=https://ollama.lan.poldebra.me
+      - OPENAI_API_BASE_URL=https://ollama.lan.poldebra.me/v1
+      - OPENAI_API_KEY=sk-no-key-required
+      - ENABLE_OLLAMA_API=false
     networks:
       internal:
         ipv4_address: 172.24.0.5

ollama/Caddyfile

@@ -21,7 +21,7 @@
           X-Forwarded-Host {host}
           X-Forwarded-Port {server_port}
         }
-        reverse_proxy 172.23.0.5:11434 {
+        reverse_proxy 172.23.0.5:8080 {
             header_up X-Forwarded-Proto {scheme}
         }
     }

ollama/Dockerfile

@@ -0,0 +1,12 @@
+# syntax=docker/dockerfile:1
+FROM ghcr.io/ggml-org/llama.cpp:server-rocm
+
+ARG LLAMA_SWAP_VERSION=v199
+ADD https://github.com/mostlygeek/llama-swap/releases/download/${LLAMA_SWAP_VERSION}/llama-swap_199_linux_amd64.tar.gz /tmp/llama-swap.tar.gz
+RUN tar -xzf /tmp/llama-swap.tar.gz -C /usr/local/bin llama-swap \
+ && chmod +x /usr/local/bin/llama-swap \
+ && rm /tmp/llama-swap.tar.gz
+
+EXPOSE 8080
+ENTRYPOINT ["/usr/local/bin/llama-swap"]
+CMD ["-config", "/etc/llama-swap/config.yaml", "-listen", ":8080"]

ollama/docker-compose.yml

@@ -1,15 +1,21 @@
 services:
   app:
-    image: ollama/ollama:rocm
+    build: .
+    image: local/llama-swap-rocm:latest
     restart: unless-stopped
     hostname: ollama
     container_name: ollama
-    user: 1000:1000
     volumes:
-      - "/srv/docker/ollama/data:/ubuntu/.ollama"
+      - "/srv/docker/ollama/data/models:/models:ro"
+      - "./llama-swap.yaml:/etc/llama-swap/config.yaml:ro"
+    environment:
+      - HIP_VISIBLE_DEVICES=0
     devices:
       - "/dev/kfd:/dev/kfd"
       - "/dev/dri:/dev/dri"
+    group_add:
+      - video
+      - render
     networks:
       internal:
         ipv4_address: 172.23.0.5

ollama/llama-swap.yaml

@@ -0,0 +1,130 @@
+healthCheckTimeout: 180
+logLevel: info
+
+models:
+  "qwen3.5:9b":
+    cmd: |
+      /app/llama-server
+      --host 0.0.0.0 --port ${PORT}
+      --model /models/Qwen3.5-9B-Q4_K_M.gguf
+      --mmproj /models/Qwen3.5-9B-mmproj-F16.gguf
+      --alias qwen3.5:9b
+      --n-gpu-layers 999
+      --ctx-size 8192
+      --flash-attn on
+      --jinja
+      --temp 0.7 --top-p 0.9
+
+  "qwen3.5:9b-32k":
+    cmd: |
+      /app/llama-server
+      --host 0.0.0.0 --port ${PORT}
+      --model /models/Qwen3.5-9B-Q4_K_M.gguf
+      --mmproj /models/Qwen3.5-9B-mmproj-F16.gguf
+      --alias qwen3.5:9b-32k
+      --n-gpu-layers 999
+      --ctx-size 32768
+      --flash-attn on
+      --jinja
+      --cache-type-k q8_0
+      --cache-type-v q8_0
+      --temp 0.7 --top-p 0.9
+
+  "qwen3.5:9b-uncensored":
+    cmd: |
+      /app/llama-server
+      --host 0.0.0.0 --port ${PORT}
+      --model /models/HauhauCS-Qwen3.5-9B-Uncensored-Aggressive.q4_k_m.gguf
+      --mmproj /models/HauhauCS-Qwen3.5-9B-Uncensored-Aggressive.mmproj.gguf
+      --alias "hf.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:q4_k_m"
+      --n-gpu-layers 999
+      --ctx-size 32768
+      --flash-attn on
+      --jinja
+      --cache-type-k q8_0
+      --cache-type-v q8_0
+      --temp 0.7 --top-p 0.9
+
+  "qwen3.5:9b-claude-4.6-opus-reasoning":
+    cmd: |
+      /app/llama-server
+      --host 0.0.0.0 --port ${PORT}
+      --model /models/Jackrong-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2.q4_k_m.gguf
+      --mmproj /models/Jackrong-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2.mmproj.gguf
+      --alias "hf.co/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF:q4_k_m"
+      --n-gpu-layers 999
+      --ctx-size 32768
+      --flash-attn on
+      --jinja
+      --cache-type-k q8_0
+      --cache-type-v q8_0
+      --temp 0.6 --top-p 0.95
+
+  "qwen3.5:9b-128k":
+    cmd: |
+      /app/llama-server
+      --host 0.0.0.0 --port ${PORT}
+      --model /models/Qwen3.5-9B-Q4_K_M.gguf
+      --mmproj /models/Qwen3.5-9B-mmproj-F16.gguf
+      --alias qwen3.5:9b-128k
+      --n-gpu-layers 999
+      --ctx-size 131072
+      --flash-attn on
+      --jinja
+      --cache-type-k q8_0
+      --cache-type-v q8_0
+      --temp 0.7 --top-p 0.9
+
+  "qwen3.5:9b-uncensored-128k":
+    cmd: |
+      /app/llama-server
+      --host 0.0.0.0 --port ${PORT}
+      --model /models/HauhauCS-Qwen3.5-9B-Uncensored-Aggressive.q4_k_m.gguf
+      --mmproj /models/HauhauCS-Qwen3.5-9B-Uncensored-Aggressive.mmproj.gguf
+      --alias "hf.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:q4_k_m"
+      --n-gpu-layers 999
+      --ctx-size 131072
+      --flash-attn on
+      --jinja
+      --cache-type-k q8_0
+      --cache-type-v q8_0
+      --temp 0.7 --top-p 0.9
+
+  "qwen3.5:9b-claude-4.6-opus-reasoning-128k":
+    cmd: |
+      /app/llama-server
+      --host 0.0.0.0 --port ${PORT}
+      --model /models/Jackrong-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2.q4_k_m.gguf
+      --mmproj /models/Jackrong-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2.mmproj.gguf
+      --alias "hf.co/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF:q4_k_m"
+      --n-gpu-layers 999
+      --ctx-size 131072
+      --flash-attn on
+      --jinja
+      --cache-type-k q8_0
+      --cache-type-v q8_0
+      --temp 0.6 --top-p 0.95
+
+  "gemma4:e4b-uncensored":
+    cmd: |
+      /app/llama-server
+      --host 0.0.0.0 --port ${PORT}
+      --model /models/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf
+      --mmproj /models/mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf
+      --alias "hf.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive:q8_k_p"
+      --n-gpu-layers 999
+      --ctx-size 8192
+      --flash-attn on
+      --jinja
+
+  "gemma4:26b-a4b":
+    cmd: |
+      /app/llama-server
+      --host 0.0.0.0 --port ${PORT}
+      --model /models/gemma-4-26B-A4B-it-UD-IQ4_NL.gguf
+      --mmproj /models/gemma-4-26B-A4B-it-UD-IQ4_NL-mmproj-BF16.gguf
+      --alias "hf.co/unsloth/gemma-4-26B-A4B-it:ud-iq4_nl"
+      --n-gpu-layers 999
+      --ctx-size 8192
+      --flash-attn on
+      --jinja