README.md
pyproject.toml
src/gallama/__init__.py
src/gallama/app.py
src/gallama/cli.py
src/gallama/constants.py
src/gallama/dependencies.py
src/gallama/dependencies_server.py
src/gallama/request_validation.py
src/gallama/server.py
src/gallama.egg-info/PKG-INFO
src/gallama.egg-info/SOURCES.txt
src/gallama.egg-info/dependency_links.txt
src/gallama.egg-info/entry_points.txt
src/gallama.egg-info/requires.txt
src/gallama.egg-info/top_level.txt
src/gallama/api_response/__init__.py
src/gallama/api_response/api_formatter.py
src/gallama/api_response/chat_response.py
src/gallama/api_response/model_response.py
src/gallama/api_response/stream_parser_v2.py
src/gallama/backend/__init__.py
src/gallama/backend/embedding/__init__.py
src/gallama/backend/embedding/embedding.py
src/gallama/backend/llm/__init__.py
src/gallama/backend/llm/format_enforcer.py
src/gallama/backend/llm/json_schema_utils.py
src/gallama/backend/llm/thinking_template.py
src/gallama/backend/llm/tools.py
src/gallama/backend/llm/engine/__init__.py
src/gallama/backend/llm/engine/base.py
src/gallama/backend/llm/engine/exllama/__init__.py
src/gallama/backend/llm/engine/exllama/exllamav2.py
src/gallama/backend/llm/engine/exllama/inference_json_lmfe_wrapper.py
src/gallama/backend/llm/engine/exllamav3/__init__.py
src/gallama/backend/llm/engine/exllamav3/exllamav3.py
src/gallama/backend/llm/engine/ik_llama/__init__.py
src/gallama/backend/llm/engine/ik_llama/ik_llama.py
src/gallama/backend/llm/engine/llamacpp/__init__.py
src/gallama/backend/llm/engine/llamacpp/llamacpp.py
src/gallama/backend/llm/engine/llamacpp_server/__init__.py
src/gallama/backend/llm/engine/llamacpp_server/llamacpp_server.py
src/gallama/backend/llm/engine/mlx_vllm/__init__.py
src/gallama/backend/llm/engine/mlx_vllm/mlx_vlm.py
src/gallama/backend/llm/engine/sglang/__init__.py
src/gallama/backend/llm/engine/sglang/sglang.py
src/gallama/backend/llm/engine/transformers/__init__.py
src/gallama/backend/llm/engine/transformers/transformers.py
src/gallama/backend/llm/engine/transformers/model_support/__init__.py
src/gallama/backend/llm/engine/transformers/model_support/llama3_2_vision/__init__.py
src/gallama/backend/llm/engine/transformers/model_support/llama3_2_vision/text_streamer.py
src/gallama/backend/llm/engine/vllm/__init__.py
src/gallama/backend/llm/engine/vllm/vllm.py
src/gallama/backend/llm/prompt_engine/__init__.py
src/gallama/backend/llm/prompt_engine/model_special_tag.py
src/gallama/backend/llm/prompt_engine/pe_custom.py
src/gallama/backend/llm/prompt_engine/pe_transformers.py
src/gallama/backend/llm/prompt_engine/prompt_engine.py
src/gallama/backend/llm/prompt_engine/by_model/__init__.py
src/gallama/backend/llm/prompt_engine/by_model/default.py
src/gallama/backend/llm/prompt_engine/by_model/gemma4.py
src/gallama/backend/llm/prompt_engine/by_model/glm4.py
src/gallama/backend/llm/prompt_engine/by_model/gpt_oss.py
src/gallama/backend/llm/prompt_engine/by_model/minimax.py
src/gallama/backend/llm/prompt_engine/by_model/ministral3.py
src/gallama/backend/llm/prompt_engine/by_model/qwen3.py
src/gallama/backend/llm/prompt_engine/by_model/qwen35.py
src/gallama/backend/stt/__init__.py
src/gallama/backend/stt/asr_processor.py
src/gallama/backend/stt/audio_buffer.py
src/gallama/backend/stt/base.py
src/gallama/backend/stt/hypothesis.py
src/gallama/backend/stt/vad.py
src/gallama/backend/stt/faster_whisper/model.py
src/gallama/backend/stt/mlx_whisper/model.py
src/gallama/backend/tts/TTSQueueHandler.py
src/gallama/backend/tts/__init__.py
src/gallama/backend/tts/base.py
src/gallama/backend/tts/text_processor.py
src/gallama/backend/tts/model/__init__.py
src/gallama/backend/tts/model/kokoro/__init__.py
src/gallama/backend/tts/model/kokoro/kokoro.py
src/gallama/config/__init__.py
src/gallama/config/config_manager.py
src/gallama/conversation_store/__init__.py
src/gallama/conversation_store/store.py
src/gallama/data/__init__.py
src/gallama/data/default_model_list.yaml
src/gallama/data/model_config.yaml
src/gallama/data/model_token.yaml
src/gallama/data/default_voice/kokoro-tts-heart.wav
src/gallama/data/thinking_template/tool_forced_evaluation.xml
src/gallama/data/thinking_template/tool_necessity_evaluation.regex
src/gallama/data/thinking_template/tool_necessity_evaluation.xml
src/gallama/data_classes/__init__.py
src/gallama/data_classes/audio_data_class.py
src/gallama/data_classes/data_class.py
src/gallama/data_classes/generation_data_class.py
src/gallama/data_classes/internal_ws.py
src/gallama/data_classes/realtime_client_proto.py
src/gallama/data_classes/realtime_server_proto.py
src/gallama/data_classes/responses_api.py
src/gallama/data_classes/server_dataclass.py
src/gallama/data_classes/video.py
src/gallama/logger/__init__.py
src/gallama/logger/logger.py
src/gallama/model_manager/ModelManager.py
src/gallama/model_manager/__init__.py
src/gallama/realtime/__init__.py
src/gallama/realtime/audio_preprocessor.py
src/gallama/realtime/message_queue.py
src/gallama/realtime/response.py
src/gallama/realtime/session_manager.py
src/gallama/realtime/vad.py
src/gallama/realtime/websocket_client.py
src/gallama/realtime/websocket_handler.py
src/gallama/realtime/websocket_manager.py
src/gallama/realtime/websocket_session.py
src/gallama/remote_mcp/__init__.py
src/gallama/remote_mcp/models.py
src/gallama/remote_mcp/orchestrator.py
src/gallama/remote_mcp/runtime.py
src/gallama/response_store/__init__.py
src/gallama/response_store/store.py
src/gallama/routes/__init__.py
src/gallama/routes/audio.py
src/gallama/routes/chat.py
src/gallama/routes/embedding.py
src/gallama/routes/model_management.py
src/gallama/routes/ws_llm.py
src/gallama/routes/ws_stt.py
src/gallama/routes/ws_tts.py
src/gallama/routes/ws_video.py
src/gallama/server_engine/__init__.py
src/gallama/server_engine/model_capabilities.py
src/gallama/server_engine/model_management.py
src/gallama/server_engine/request_handler.py
src/gallama/server_engine/request_routing.py
src/gallama/server_engine/responses_ws_bridge.py
src/gallama/server_engine/server_manager.py
src/gallama/server_routes/__init__.py
src/gallama/server_routes/realtime.py
src/gallama/server_routes/responses_ws.py
src/gallama/server_routes/server_management.py
src/gallama/utils/__init__.py
src/gallama/utils/audio_processor_utils.py
src/gallama/utils/request_disconnect.py
src/gallama/utils/utils.py