Add new model files and update Ansible playbooks for Qwen3.5 and Qwen3.6

- Created model files for Qwen3.5 with different context lengths.
- Added a new Ansible host variable file for CI server configuration.
- Updated GPU server host variables to include Ollama models and model files.
- Enhanced playbooks for Podman to manage Ollama models, including copying model files and checking existing models.
- Introduced a new playbook for setting up Qwen3.6 with specific configurations.
- Updated Windows SSH tasks to improve security and configuration management.
- Added a Python utility to parse Ollama model names from command output.
- Modified Terraform configurations to include new DNS entries and proxy settings.
- Improved Nginx proxy configurations with timeout settings.
This commit is contained in:
2026-05-27 23:53:00 +02:00
parent dd943c8963
commit e9e28a5ca8
27 changed files with 611 additions and 103 deletions
@@ -0,0 +1,11 @@
FROM ghcr.io/ggml-org/llama.cpp:server-cuda
ARG UID=1000
ARG GID=1000
RUN groupadd --system --gid ${GID} worker && \
useradd --system --gid ${GID} --uid ${UID} --home /home/worker worker && \
mkdir -p /home/worker && chown worker:worker /home/worker
WORKDIR /home/worker
USER worker
ENTRYPOINT ["/app/llama-server"]
@@ -0,0 +1,2 @@
FROM gemma4:e4b
PARAMETER num_ctx 32359
@@ -0,0 +1,2 @@
FROM gpt-oss:latest
PARAMETER num_ctx 32359
@@ -0,0 +1,2 @@
FROM qwen3.5:9b
PARAMETER num_ctx 32359
@@ -0,0 +1,2 @@
FROM qwen3.5:9b
PARAMETER num_ctx 65359
@@ -0,0 +1,2 @@
FROM qwen3.5:9b
PARAMETER num_ctx 32359
@@ -0,0 +1,2 @@
FROM qwen3.5:9b
PARAMETER num_ctx 65537
+5
View File
@@ -0,0 +1,5 @@
By accessing this system, you consent to the following conditions:
- This system is for authorized use only.
- Any or all uses of this system and all files on this system may be monitored.
- Communications using, or data stored on, this system are not private.