LICENSE
README.md
pyproject.toml
tests/test_anthropic_adapter.py
tests/test_api_models.py
tests/test_api_utils.py
tests/test_audio.py
tests/test_audit_fixes.py
tests/test_batching.py
tests/test_batching_deterministic.py
tests/test_block_disk_bfloat16.py
tests/test_cache_bypass.py
tests/test_cache_fixes.py
tests/test_cache_isolation.py
tests/test_cache_types.py
tests/test_cancellation.py
tests/test_cli_commands.py
tests/test_continuous_batching.py
tests/test_disk_cache_unit.py
tests/test_e2e_live.py
tests/test_embeddings.py
tests/test_emoji_comprehensive.py
tests/test_engine_audit.py
tests/test_flash_moe_loader.py
tests/test_gemma3_27b_comprehensive.py
tests/test_health_endpoint.py
tests/test_hybrid_batching.py
tests/test_hybrid_prefix_cache.py
tests/test_image_api.py
tests/test_image_gen.py
tests/test_image_gen_engine.py
tests/test_jang_loader.py
tests/test_jit_toggle.py
tests/test_kv_quant.py
tests/test_llm.py
tests/test_mcp_security.py
tests/test_medgemma_comprehensive.py
tests/test_memory_cache.py
tests/test_mllm.py
tests/test_mllm_cache.py
tests/test_mllm_continuous_batching.py
tests/test_mllm_message_serialization.py
tests/test_mllm_scheduler_cache.py
tests/test_mllm_scheduler_stability.py
tests/test_model_config_registry.py
tests/test_model_inspector.py
tests/test_model_name.py
tests/test_model_registry.py
tests/test_native_tool_format.py
tests/test_optimizations.py
tests/test_paged_cache.py
tests/test_paged_cache_benefits.py
tests/test_paged_cache_real_inference.py
tests/test_paged_cache_real_model.py
tests/test_paged_cache_unit.py
tests/test_platform.py
tests/test_prefix_cache.py
tests/test_reasoning_parser.py
tests/test_reasoning_tool_interaction.py
tests/test_request.py
tests/test_request_cancellation.py
tests/test_reranker_endpoint.py
tests/test_server.py
tests/test_simple_engine.py
tests/test_speculative.py
tests/test_ssm_companion_cache.py
tests/test_streaming_detokenizer.py
tests/test_streaming_json_encoder.py
tests/test_streaming_latency.py
tests/test_streaming_reasoning.py
tests/test_structured_output.py
tests/test_tool_fallback_injection.py
tests/test_tool_format.py
tests/test_tool_parsers.py
tests/test_tq_disk_cache.py
tests/test_tq_e2e_live.py
vmlx.egg-info/PKG-INFO
vmlx.egg-info/SOURCES.txt
vmlx.egg-info/dependency_links.txt
vmlx.egg-info/entry_points.txt
vmlx.egg-info/requires.txt
vmlx.egg-info/top_level.txt
vmlx_engine/__init__.py
vmlx_engine/attention.py
vmlx_engine/benchmark.py
vmlx_engine/block_disk_store.py
vmlx_engine/cli.py
vmlx_engine/disk_cache.py
vmlx_engine/embedding.py
vmlx_engine/engine_core.py
vmlx_engine/flash_moe_config.py
vmlx_engine/gradio_app.py
vmlx_engine/gradio_text_app.py
vmlx_engine/image_gen.py
vmlx_engine/memory_cache.py
vmlx_engine/mllm_batch_generator.py
vmlx_engine/mllm_cache.py
vmlx_engine/mllm_scheduler.py
vmlx_engine/mlx_platform.py
vmlx_engine/model_config_registry.py
vmlx_engine/model_configs.py
vmlx_engine/model_registry.py
vmlx_engine/model_runner.py
vmlx_engine/multimodal_processor.py
vmlx_engine/optimizations.py
vmlx_engine/output_collector.py
vmlx_engine/paged_cache.py
vmlx_engine/plugin.py
vmlx_engine/prefix_cache.py
vmlx_engine/prompt_lookup.py
vmlx_engine/request.py
vmlx_engine/reranker.py
vmlx_engine/scheduler.py
vmlx_engine/server.py
vmlx_engine/simple.py
vmlx_engine/speculative.py
vmlx_engine/state_machine.py
vmlx_engine/tq_disk_store.py
vmlx_engine/vision_embedding_cache.py
vmlx_engine/worker.py
vmlx_engine/api/__init__.py
vmlx_engine/api/anthropic_adapter.py
vmlx_engine/api/models.py
vmlx_engine/api/ollama_adapter.py
vmlx_engine/api/streaming.py
vmlx_engine/api/tool_calling.py
vmlx_engine/api/utils.py
vmlx_engine/audio/__init__.py
vmlx_engine/audio/processor.py
vmlx_engine/audio/stt.py
vmlx_engine/audio/tts.py
vmlx_engine/cache/__init__.py
vmlx_engine/cache/codebook_cache.py
vmlx_engine/commands/__init__.py
vmlx_engine/commands/convert.py
vmlx_engine/commands/doctor.py
vmlx_engine/commands/info.py
vmlx_engine/commands/list.py
vmlx_engine/config/__init__.py
vmlx_engine/config/manager.py
vmlx_engine/config/models.py
vmlx_engine/config/sources/__init__.py
vmlx_engine/config/sources/cli_source.py
vmlx_engine/config/sources/env_source.py
vmlx_engine/config/sources/yaml_source.py
vmlx_engine/distributed/__init__.py
vmlx_engine/distributed/cli.py
vmlx_engine/distributed/coordinator.py
vmlx_engine/distributed/discovery.py
vmlx_engine/distributed/engine.py
vmlx_engine/distributed/layer_assign.py
vmlx_engine/distributed/mesh_election.py
vmlx_engine/distributed/mesh_manager.py
vmlx_engine/distributed/mesh_node.py
vmlx_engine/distributed/mesh_topology.py
vmlx_engine/distributed/protocol.py
vmlx_engine/distributed/tensor_parallel.py
vmlx_engine/distributed/worker.py
vmlx_engine/engine/__init__.py
vmlx_engine/engine/base.py
vmlx_engine/engine/batched.py
vmlx_engine/engine/simple.py
vmlx_engine/mcp/__init__.py
vmlx_engine/mcp/client.py
vmlx_engine/mcp/config.py
vmlx_engine/mcp/executor.py
vmlx_engine/mcp/manager.py
vmlx_engine/mcp/security.py
vmlx_engine/mcp/tools.py
vmlx_engine/mcp/types.py
vmlx_engine/metal/__init__.py
vmlx_engine/metal/kernel_manager.py
vmlx_engine/models/__init__.py
vmlx_engine/models/_gemma4_text_upstream.py
vmlx_engine/models/_gemma4_upstream.py
vmlx_engine/models/codebook.py
vmlx_engine/models/codebook_expert_loader.py
vmlx_engine/models/codebook_moe_integration.py
vmlx_engine/models/flash_moe_integration.py
vmlx_engine/models/gemma4_native_register.py
vmlx_engine/models/llm.py
vmlx_engine/models/mllm.py
vmlx_engine/reasoning/__init__.py
vmlx_engine/reasoning/base.py
vmlx_engine/reasoning/deepseek_r1_parser.py
vmlx_engine/reasoning/gemma4_parser.py
vmlx_engine/reasoning/gptoss_parser.py
vmlx_engine/reasoning/mistral_parser.py
vmlx_engine/reasoning/qwen3_parser.py
vmlx_engine/reasoning/think_parser.py
vmlx_engine/tests/test_codebook_inference.py
vmlx_engine/tests/test_codebook_kernels.py
vmlx_engine/tool_parsers/__init__.py
vmlx_engine/tool_parsers/abstract_tool_parser.py
vmlx_engine/tool_parsers/auto_tool_parser.py
vmlx_engine/tool_parsers/deepseek_tool_parser.py
vmlx_engine/tool_parsers/functionary_tool_parser.py
vmlx_engine/tool_parsers/gemma4_tool_parser.py
vmlx_engine/tool_parsers/glm47_tool_parser.py
vmlx_engine/tool_parsers/granite_tool_parser.py
vmlx_engine/tool_parsers/hermes_tool_parser.py
vmlx_engine/tool_parsers/kimi_tool_parser.py
vmlx_engine/tool_parsers/llama_tool_parser.py
vmlx_engine/tool_parsers/minimax_tool_parser.py
vmlx_engine/tool_parsers/mistral_tool_parser.py
vmlx_engine/tool_parsers/nemotron_tool_parser.py
vmlx_engine/tool_parsers/qwen_tool_parser.py
vmlx_engine/tool_parsers/step3p5_tool_parser.py
vmlx_engine/tool_parsers/xlam_tool_parser.py
vmlx_engine/utils/__init__.py
vmlx_engine/utils/cache_types.py
vmlx_engine/utils/chat_templates.py
vmlx_engine/utils/flash_moe_loader.py
vmlx_engine/utils/jang_loader.py
vmlx_engine/utils/mamba_cache.py
vmlx_engine/utils/mlx_vlm_compat.py
vmlx_engine/utils/model_inspector.py
vmlx_engine/utils/nemotron_latent_moe.py
vmlx_engine/utils/smelt_loader.py
vmlx_engine/utils/ssm_companion_cache.py
vmlx_engine/utils/tokenizer.py