README.md
pyproject.toml
rapid_mlx.egg-info/PKG-INFO
rapid_mlx.egg-info/SOURCES.txt
rapid_mlx.egg-info/dependency_links.txt
rapid_mlx.egg-info/entry_points.txt
rapid_mlx.egg-info/requires.txt
rapid_mlx.egg-info/top_level.txt
tests/test_anthropic_adapter.py
tests/test_anthropic_models.py
tests/test_api_models.py
tests/test_api_utils.py
tests/test_audio.py
tests/test_batching.py
tests/test_batching_deterministic.py
tests/test_cloud_router.py
tests/test_continuous_batching.py
tests/test_deltanet_cache.py
tests/test_deltanet_snapshot.py
tests/test_embeddings.py
tests/test_engine_parity.py
tests/test_event_loop.py
tests/test_guided.py
tests/test_harmony_parsers.py
tests/test_hybrid.py
tests/test_kv_cache_quantization.py
tests/test_llm.py
tests/test_llm_cache.py
tests/test_mcp_security.py
tests/test_memory_cache.py
tests/test_memory_stability.py
tests/test_minimax_reasoning_parser.py
tests/test_minimax_tool_parser.py
tests/test_mllm.py
tests/test_mllm_cache.py
tests/test_mllm_continuous_batching.py
tests/test_mllm_stream_lock.py
tests/test_model_aliases.py
tests/test_model_auto_config.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_platform.py
tests/test_prefix_cache.py
tests/test_prompt_lookup.py
tests/test_prompt_lookup_bench.py
tests/test_reasoning_parser.py
tests/test_reasoning_parsers.py
tests/test_request.py
tests/test_server.py
tests/test_server_utils.py
tests/test_simple_engine.py
tests/test_simple_engine_unit.py
tests/test_streaming.py
tests/test_streaming_detokenizer.py
tests/test_streaming_json_encoder.py
tests/test_streaming_latency.py
tests/test_streaming_newlines.py
tests/test_streaming_simulator.py
tests/test_structured_output.py
tests/test_tool_call_e2e.py
tests/test_tool_calling.py
tests/test_tool_injection.py
tests/test_tool_logits.py
tests/test_tool_parsers.py
tests/test_upstream_regression.py
vllm_mlx/__init__.py
vllm_mlx/aliases.json
vllm_mlx/attention.py
vllm_mlx/benchmark.py
vllm_mlx/cli.py
vllm_mlx/cloud_router.py
vllm_mlx/embedding.py
vllm_mlx/engine_core.py
vllm_mlx/gradio_app.py
vllm_mlx/gradio_text_app.py
vllm_mlx/memory_cache.py
vllm_mlx/mllm_batch_generator.py
vllm_mlx/mllm_cache.py
vllm_mlx/mllm_scheduler.py
vllm_mlx/model_aliases.py
vllm_mlx/model_auto_config.py
vllm_mlx/model_registry.py
vllm_mlx/model_runner.py
vllm_mlx/multimodal_processor.py
vllm_mlx/optimizations.py
vllm_mlx/output_collector.py
vllm_mlx/paged_cache.py
vllm_mlx/platform.py
vllm_mlx/plugin.py
vllm_mlx/prefix_cache.py
vllm_mlx/request.py
vllm_mlx/scheduler.py
vllm_mlx/server.py
vllm_mlx/vision_embedding_cache.py
vllm_mlx/worker.py
vllm_mlx/api/__init__.py
vllm_mlx/api/anthropic_adapter.py
vllm_mlx/api/anthropic_models.py
vllm_mlx/api/guided.py
vllm_mlx/api/harmony_tools.py
vllm_mlx/api/models.py
vllm_mlx/api/streaming.py
vllm_mlx/api/tool_calling.py
vllm_mlx/api/tool_logits.py
vllm_mlx/api/utils.py
vllm_mlx/audio/__init__.py
vllm_mlx/audio/processor.py
vllm_mlx/audio/stt.py
vllm_mlx/audio/tts.py
vllm_mlx/engine/__init__.py
vllm_mlx/engine/base.py
vllm_mlx/engine/batched.py
vllm_mlx/engine/hybrid.py
vllm_mlx/engine/simple.py
vllm_mlx/mcp/__init__.py
vllm_mlx/mcp/client.py
vllm_mlx/mcp/config.py
vllm_mlx/mcp/executor.py
vllm_mlx/mcp/manager.py
vllm_mlx/mcp/security.py
vllm_mlx/mcp/tools.py
vllm_mlx/mcp/types.py
vllm_mlx/models/__init__.py
vllm_mlx/models/llm.py
vllm_mlx/models/mllm.py
vllm_mlx/patches/__init__.py
vllm_mlx/patches/qwen3_next_mtp.py
vllm_mlx/reasoning/__init__.py
vllm_mlx/reasoning/base.py
vllm_mlx/reasoning/deepseek_r1_parser.py
vllm_mlx/reasoning/gpt_oss_parser.py
vllm_mlx/reasoning/harmony_parser.py
vllm_mlx/reasoning/minimax_parser.py
vllm_mlx/reasoning/qwen3_parser.py
vllm_mlx/reasoning/think_parser.py
vllm_mlx/speculative/__init__.py
vllm_mlx/speculative/prompt_lookup.py
vllm_mlx/tool_parsers/__init__.py
vllm_mlx/tool_parsers/abstract_tool_parser.py
vllm_mlx/tool_parsers/auto_tool_parser.py
vllm_mlx/tool_parsers/deepseek_tool_parser.py
vllm_mlx/tool_parsers/deepseekv31_tool_parser.py
vllm_mlx/tool_parsers/functionary_tool_parser.py
vllm_mlx/tool_parsers/glm47_tool_parser.py
vllm_mlx/tool_parsers/granite_tool_parser.py
vllm_mlx/tool_parsers/harmony_tool_parser.py
vllm_mlx/tool_parsers/hermes_tool_parser.py
vllm_mlx/tool_parsers/kimi_tool_parser.py
vllm_mlx/tool_parsers/llama_tool_parser.py
vllm_mlx/tool_parsers/minimax_tool_parser.py
vllm_mlx/tool_parsers/mistral_tool_parser.py
vllm_mlx/tool_parsers/nemotron_tool_parser.py
vllm_mlx/tool_parsers/qwen3coder_tool_parser.py
vllm_mlx/tool_parsers/qwen_tool_parser.py
vllm_mlx/tool_parsers/seed_oss_tool_parser.py
vllm_mlx/tool_parsers/xlam_tool_parser.py
vllm_mlx/utils/__init__.py
vllm_mlx/utils/chat_template.py
vllm_mlx/utils/chat_templates.py
vllm_mlx/utils/decode.py
vllm_mlx/utils/mamba_cache.py
vllm_mlx/utils/tokenizer.py