Leonid PershinandCursor 5d0c30f66b Enhance Ollama integration and model management ...

- Implemented support for parallel embedding in Ollama, allowing for improved performance in chat and memory functions.
- Updated the `ollama-roles.json` and CPU Modelfile to accommodate new features.
- Increased the maximum loaded models and parallel processing limits to 2, optimizing resource usage.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-08-21 23:05:48 +03:00

..

conftest.py

Refactor environment and configuration management

2026-08-21 03:20:18 +03:00

test_access_card.py

Enhance error handling and state management in access card and session modules

2026-08-21 20:20:49 +03:00

test_balance.py

Implement balance monitoring and notification for Selectel API integration

2026-08-21 06:52:51 +03:00

test_bootstrap.py

Enhance Ollama model management and performance tuning

2026-08-21 14:20:06 +03:00

test_capture_merge.py

Add Hugging Face support and enhance model resolution logic

2026-08-21 07:34:15 +03:00

test_civitai_fetch.py

Add file size conversion and enhance Civitai job processing

2026-08-21 10:52:44 +03:00

test_cli.py

Update configuration and documentation for LLM support and local watchdog

2026-08-21 05:29:23 +03:00

test_clone_ext_update.py

Add support for gpu-rent.vars and enhance git update functionality

2026-08-21 05:01:53 +03:00

test_cloud.py

Add package data for GPU rent and update CLI documentation

2026-08-21 03:06:51 +03:00

test_config.py

Refactor environment and configuration management

2026-08-21 03:20:18 +03:00

test_hold_killer.py

Refactor backend status handling and improve idle management

2026-08-21 10:07:16 +03:00

test_huggingface.py

Add Hugging Face support and enhance model resolution logic

2026-08-21 07:34:15 +03:00

test_inventory.py

Add package data for GPU rent and update CLI documentation

2026-08-21 03:06:51 +03:00

test_launchers.py

Refactor environment and configuration management

2026-08-21 03:20:18 +03:00

test_llm_only.py

Refactor LLM configuration to remove llamacpp support

2026-08-21 08:51:36 +03:00

test_llm_runtime.py

Warm Ollama into VRAM on up and tunnel so Assistent chat is not cold.

2026-08-21 20:47:14 +03:00

test_local_watchdog.py

Update configuration and documentation for LLM support and local watchdog

2026-08-21 05:29:23 +03:00

test_manifests.py

Refactor LLM configuration to remove llamacpp support

2026-08-21 08:51:36 +03:00

test_migrate_local_configs.py

Enhance Ollama integration and model management

2026-08-21 23:05:48 +03:00

test_ollama_model_use.py

Support Ollama use: chat|memory and parallel embed beside VL.

2026-08-21 22:47:03 +03:00

test_ollama_pull.py

Enhance Ollama model management and performance tuning

2026-08-21 14:20:06 +03:00

test_ollama_warmup.py

Warm Ollama into VRAM on up and tunnel so Assistent chat is not cold.

2026-08-21 20:47:14 +03:00

test_perf_tiers.py

Support Ollama use: chat|memory and parallel embed beside VL.

2026-08-21 22:47:03 +03:00

test_pools.py

Refactor access card printing and update test assertions

2026-08-21 06:34:45 +03:00

test_prompts.py

Refactor access card printing and update test assertions

2026-08-21 06:34:45 +03:00

test_ready_snapshot.py

Refactor LLM configuration to remove llamacpp support

2026-08-21 08:51:36 +03:00

test_remote_llm_env.py

Refactor LLM configuration to remove llamacpp support

2026-08-21 08:51:36 +03:00

test_resize.py

Bump version to 0.2.0 and enhance documentation

2026-08-21 03:38:01 +03:00

test_seed.py

Add support for Gitea and Forgejo in token handling

2026-08-21 10:45:54 +03:00

test_server_plan.py

Refactor LLM configuration to remove llamacpp support

2026-08-21 08:51:36 +03:00

test_session.py

Enhance error handling and state management in access card and session modules

2026-08-21 20:20:49 +03:00

test_ssh_stream.py

Enhance logging and progress handling in SSH operations

2026-08-21 07:20:28 +03:00

test_sshtunnel_shim.py

Add support for gpu-rent.vars and enhance git update functionality

2026-08-21 05:01:53 +03:00

test_swarmui_api_keys.py

Enhance SwarmUI integration and GPU environment verification

2026-08-21 07:09:20 +03:00

test_term.py

Refactor access card printing and update test assertions

2026-08-21 06:34:45 +03:00

test_timing.py

Enhance logging and timing in CLI and session operations

2026-08-21 08:03:04 +03:00

test_tune_swarm_perf.py

Enhance error handling and state management in access card and session modules

2026-08-21 20:20:49 +03:00

test_tunnel_watch.py

Warm Ollama into VRAM on up and tunnel so Assistent chat is not cold.

2026-08-21 20:47:14 +03:00

test_up_stop_on_fail.py

Implement UP_STOP_ON_FAIL option to manage GPU state on installation failure

2026-08-21 08:32:33 +03:00

test_user_data.py

Implement SSH user data handling and adjust volume size

2026-08-21 04:35:02 +03:00

test_ux.py

Bump version to 0.2.0 and enhance documentation

2026-08-21 03:38:01 +03:00

test_varsfile.py

Add support for gpu-rent.vars and enhance git update functionality

2026-08-21 05:01:53 +03:00

test_verify_stack.py

Enhance Ollama model management and performance tuning

2026-08-21 14:20:06 +03:00

test_wait_backend_idle.py

Update documentation and CLI behavior for GPU management

2026-08-21 13:25:55 +03:00

test_warm_up_skips.py

Warm Ollama into VRAM on up and tunnel so Assistent chat is not cold.

2026-08-21 20:47:14 +03:00