LICENSE
LICENSE-APACHE
NOTICE
README.md
pyproject.toml
qmlx_serve.egg-info/PKG-INFO
qmlx_serve.egg-info/SOURCES.txt
qmlx_serve.egg-info/dependency_links.txt
qmlx_serve.egg-info/entry_points.txt
qmlx_serve.egg-info/requires.txt
qmlx_serve.egg-info/top_level.txt
tests/test_447_stream_tool_choice_auto.py
tests/test_agent_query_context_skip.py
tests/test_agent_test_runner_refresh_config.py
tests/test_alias_hybrid_classification.py
tests/test_alias_recommended_sampling.py
tests/test_aliases_contract.py
tests/test_anthropic_adapter.py
tests/test_anthropic_models.py
tests/test_anthropic_output_config.py
tests/test_anthropic_route_auth.py
tests/test_anthropic_route_streaming.py
tests/test_anthropic_route_thinking_gate.py
tests/test_anthropic_spec_polish_bundle.py
tests/test_anthropic_stop_sequences.py
tests/test_anthropic_stream_finalize.py
tests/test_anthropic_stream_reasoning.py
tests/test_anthropic_streaming_reasoning.py
tests/test_anthropic_think_leak_r12_m1b.py
tests/test_anthropic_tool_choice_validation.py
tests/test_anthropic_tool_param_validation.py
tests/test_anthropic_tool_usage_d.py
tests/test_anthropic_tool_validation_scope.py
tests/test_api_models.py
tests/test_api_utils.py
tests/test_api_validation_bundle.py
tests/test_batched_engine_chat_template.py
tests/test_batched_engine_output_router.py
tests/test_batched_engine_tool_call_normalization.py
tests/test_batching.py
tests/test_batching_deterministic.py
tests/test_bench_vs_ollama.py
tests/test_body_receive_timeout.py
tests/test_cache_routes.py
tests/test_cancelled_requests_metric.py
tests/test_capabilities_field.py
tests/test_casual_chat_auto_disable_thinking.py
tests/test_chat_logprobs_channel_routing.py
tests/test_chat_n_must_equal_1.py
tests/test_chat_route_forced_tool_prefix.py
tests/test_chat_route_forced_tool_prefix_wiring.py
tests/test_chat_route_tool_choice_enforcement.py
tests/test_chat_route_tool_tag_leak.py
tests/test_chat_streaming_guided.py
tests/test_chat_streaming_no_reasoning_alias.py
tests/test_chat_streaming_spec.py
tests/test_chat_template_kwargs.py
tests/test_chat_template_marker_sanitize.py
tests/test_chat_template_sidecar.py
tests/test_chat_template_tool_call_arguments.py
tests/test_check_gha_pinning.py
tests/test_check_mlx_upstream_calls.py
tests/test_clean_error_messages.py
tests/test_cli_argcomplete.py
tests/test_cli_chat.py
tests/test_cli_config_fidelity.py
tests/test_cli_info.py
tests/test_cli_jlens.py
tests/test_cli_models.py
tests/test_cloud_router.py
tests/test_codex_profile.py
tests/test_completions_log_redaction.py
tests/test_completions_response_format_json_schema.py
tests/test_completions_response_format_logprobs.py
tests/test_completions_spec_parity.py
tests/test_config_and_middleware.py
tests/test_content_block_strict_types.py
tests/test_context_length_exceeded.py
tests/test_context_overflow_400.py
tests/test_continuous_batching.py
tests/test_cors_env_configurable.py
tests/test_cors_lockdown_response_shape.py
tests/test_d_anthro_validation.py
tests/test_ddtree_eligibility.py
tests/test_ddtree_integration.py
tests/test_deep_nest_dos.py
tests/test_deepseek_v32_indexer_gate.py
tests/test_dense_sampler_fastpath.py
tests/test_dequantize_cache.py
tests/test_dflash_adapter_signature.py
tests/test_dflash_eligibility.py
tests/test_dflash_integration.py
tests/test_dflash_spec_decode.py
tests/test_diffusion_engine.py
tests/test_disconnect_counter_prod_shape.py
tests/test_disconnect_guard_aborts_scheduler.py
tests/test_disk_kv_checkpoint.py
tests/test_disk_space_check.py
tests/test_download_gate.py
tests/test_enable_thinking_prompt_accounting.py
tests/test_enable_thinking_warning_header.py
tests/test_engine_router_non_stream.py
tests/test_engine_step_thread.py
tests/test_envelope_field_extraction.py
tests/test_event_loop.py
tests/test_exception_handlers.py
tests/test_generation_config_loader.py
tests/test_guided.py
tests/test_harmony_stop_final_channel_only.py
tests/test_healthz_perf_budget.py
tests/test_help_fuzzy.py
tests/test_hermes_harness_contract.py
tests/test_honest_metrics.py
tests/test_hy3_chat_template_default.py
tests/test_idle_event_wakeup.py
tests/test_image_block_requires_vision_model.py
tests/test_image_url_must_be_object.py
tests/test_internal_route_auth.py
tests/test_kv_cache_dtype.py
tests/test_kv_cache_dtype_cli.py
tests/test_kv_cache_dtype_metrics.py
tests/test_kv_cache_position_ids.py
tests/test_launch_cli.py
tests/test_legacy_functions_field.py
tests/test_log_namespace_rebrand.py
tests/test_lone_surrogate_validator.py
tests/test_max_generation_tokens_ceiling.py
tests/test_max_tokens_resolver.py
tests/test_mcp_config_discovery.py
tests/test_mcp_security.py
tests/test_memory_cache.py
tests/test_memory_capacity_check.py
tests/test_memory_stability.py
tests/test_metal_cap_enforcement.py
tests/test_metal_error_recovery.py
tests/test_metrics_route.py
tests/test_mirror_pull.py
tests/test_mirror_to_r2.py
tests/test_mlx_compat.py
tests/test_modality_field.py
tests/test_model_aliases.py
tests/test_model_auto_config.py
tests/test_model_profiles_ssot.py
tests/test_model_registry.py
tests/test_models_command_layout.py
tests/test_mtp_cli_wiring.py
tests/test_mtp_gemma4_assistant_inject.py
tests/test_mtp_inject_and_install.py
tests/test_mtp_lossless.py
tests/test_mtp_real_weights.py
tests/test_mtp_spec_decode.py
tests/test_mtp_stream_contract.py
tests/test_mxfp4_moe_guardrail.py
tests/test_native_tool_format.py
tests/test_no_out_of_band_routing.py
tests/test_no_pydantic_error_leak.py
tests/test_openai_tool_choice_validation.py
tests/test_optimizations.py
tests/test_orphan_tool_validation.py
tests/test_output_router.py
tests/test_packaging_data_files.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_paired_compat.py
tests/test_parallel_tool_calls.py
tests/test_param_validation_r5e.py
tests/test_param_validation_r7b.py
tests/test_parent_watchdog.py
tests/test_per_request_thinking_budget.py
tests/test_pflash.py
tests/test_pflash_engine.py
tests/test_pflash_metrics.py
tests/test_pflash_needle.py
tests/test_pflash_scheduler.py
tests/test_platform.py
tests/test_postprocessor.py
tests/test_prefix_boundary_path_parity.py
tests/test_prefix_cache.py
tests/test_prefix_cache_persistence.py
tests/test_probe_fastpath.py
tests/test_prompt_lookup.py
tests/test_prompt_lookup_bench.py
tests/test_pull_summary.py
tests/test_r10_scrub_validation_bundle.py
tests/test_r12_4_strict_json_schema_constraint_matrix.py
tests/test_r12_4_strict_json_schema_helpers.py
tests/test_r12_h06_repair_context_guard.py
tests/test_r12_m3_responses_stream_leading_items_order.py
tests/test_r12_reasoning_sanitizer_required.py
tests/test_r15_routes_stability_batch.py
tests/test_ready_banner_timing.py
tests/test_reasoning_content_null_rescue.py
tests/test_reasoning_effort_translation.py
tests/test_reasoning_parser.py
tests/test_reasoning_parser_truncation_finalize.py
tests/test_release_check_m3_port_thread.py
tests/test_release_check_random.py
tests/test_request.py
tests/test_request_body_size_limit.py
tests/test_request_cancellation.py
tests/test_response_format_json_schema_strict.py
tests/test_response_format_streaming_fence_strip.py
tests/test_response_format_strict_types.py
tests/test_responses_591_followups.py
tests/test_responses_adapter.py
tests/test_responses_budget_exhaust_streaming.py
tests/test_responses_bundle.py
tests/test_responses_chat_template_kwargs.py
tests/test_responses_engine_failure_envelope.py
tests/test_responses_input_default_type.py
tests/test_responses_param_validation.py
tests/test_responses_route.py
tests/test_responses_sse_event_order.py
tests/test_rm_command.py
tests/test_route_engine_contract.py
tests/test_routes.py
tests/test_routes_cached_tokens.py
tests/test_routes_models.py
tests/test_routes_models_effective_parsers.py
tests/test_rst_mid_sse_zombie_kv.py
tests/test_runtime_cache_path.py
tests/test_sampler_fast_path.py
tests/test_sampling_param_finite_range.py
tests/test_sampling_params_passthrough.py
tests/test_sampling_validation.py
tests/test_sanitize_output.py
tests/test_scheduler_disk_kv_hook.py
tests/test_scheduler_stop_decoder_surface.py
tests/test_schema_v2_accepts_minimal_v2.py
tests/test_schema_v2_accepts_v1.py
tests/test_schema_v2_rejects_partial_harness.py
tests/test_seed_reproducibility.py
tests/test_serve_host_loopback_default.py
tests/test_serve_listen_fd.py
tests/test_serve_port_collision.py
tests/test_server.py
tests/test_server_api_key_env_fallback.py
tests/test_server_auth_ordering.py
tests/test_server_load_model_order.py
tests/test_server_utils.py
tests/test_signal_observability.py
tests/test_speculative_config.py
tests/test_sse_keepalive.py
tests/test_stop_matcher_completions.py
tests/test_stop_string_enforcement.py
tests/test_stream_forced_tool_reasoning.py
tests/test_stream_include_usage_honored.py
tests/test_streaming.py
tests/test_streaming_detokenizer.py
tests/test_streaming_detokenizer_bpe.py
tests/test_streaming_json_encoder.py
tests/test_streaming_latency.py
tests/test_streaming_newlines.py
tests/test_streaming_pipeline_integration.py
tests/test_streaming_reasoning_split_r8c.py
tests/test_streaming_reasoning_with_structured_output.py
tests/test_streaming_simulator.py
tests/test_streaming_think_router.py
tests/test_streaming_tool_filter.py
tests/test_stress_test_stream_usage.py
tests/test_structured_output.py
tests/test_submit_gitignore.py
tests/test_suffix_bench_methodology.py
tests/test_suffix_decoding.py
tests/test_suffix_decoding_tier.py
tests/test_telemetry_cli.py
tests/test_telemetry_consent.py
tests/test_telemetry_emit.py
tests/test_telemetry_queue.py
tests/test_telemetry_redact.py
tests/test_telemetry_state.py
tests/test_telemetry_transport.py
tests/test_tempfile_safe.py
tests/test_text_only_media_gate.py
tests/test_tokenizer_gemma4_hybrid.py
tests/test_tool_call_e2e.py
tests/test_tool_call_promotion.py
tests/test_tool_call_streaming_parity.py
tests/test_tool_calling.py
tests/test_tool_choice_enforcement.py
tests/test_tool_injection.py
tests/test_tool_logits.py
tests/test_tool_logits_schema_guards.py
tests/test_tool_param_enforcement.py
tests/test_tool_param_enforcement_f141a.py
tests/test_tool_parser_coverage.py
tests/test_tool_parser_wire_formats.py
tests/test_tool_parsers.py
tests/test_tool_result_content_array.py
tests/test_tools_auto_disable_thinking.py
tests/test_truncation_no_synthetic_text.py
tests/test_turboquant.py
tests/test_turboquant_k8v4.py
tests/test_turboquant_kvcache_state.py
tests/test_ubc_evict.py
tests/test_upgrade_cli.py
tests/test_validate_release_subject.py
tests/test_version_check.py
tests/test_vibethinker_function_xml.py
tests/test_vision_extra_install.py
tests/test_xfail_audit.py
vllm_mlx/__init__.py
vllm_mlx/_completion.py
vllm_mlx/_download_gate.py
vllm_mlx/_log_namespace.py
vllm_mlx/_mirror.py
vllm_mlx/_mlx_compat.py
vllm_mlx/_mxfp4_moe_guardrail.py
vllm_mlx/_parent_watchdog.py
vllm_mlx/_sampler_fast_path.py
vllm_mlx/_seeded_sampler.py
vllm_mlx/_signal_observability.py
vllm_mlx/_tempfile_safe.py
vllm_mlx/_version_check.py
vllm_mlx/aliases.json
vllm_mlx/attention.py
vllm_mlx/cli.py
vllm_mlx/cloud_router.py
vllm_mlx/engine_core.py
vllm_mlx/gradio_app.py
vllm_mlx/honest_metrics.py
vllm_mlx/jlens.py
vllm_mlx/kv_cache_dtype.py
vllm_mlx/memory_cache.py
vllm_mlx/model_aliases.py
vllm_mlx/model_auto_config.py
vllm_mlx/model_registry.py
vllm_mlx/model_runner.py
vllm_mlx/optimizations.py
vllm_mlx/output_collector.py
vllm_mlx/output_router.py
vllm_mlx/output_router_harmony.py
vllm_mlx/paged_cache.py
vllm_mlx/pflash.py
vllm_mlx/plugin.py
vllm_mlx/positioned_kv_cache.py
vllm_mlx/prefix_cache.py
vllm_mlx/request.py
vllm_mlx/scheduler.py
vllm_mlx/server.py
vllm_mlx/turboquant.py
vllm_mlx/vllm_platform.py
vllm_mlx/worker.py
vllm_mlx/_integration_tests/__init__.py
vllm_mlx/_integration_tests/test_aider.sh
vllm_mlx/_integration_tests/test_anthropic_sdk.py
vllm_mlx/_integration_tests/test_hermes.py
vllm_mlx/_integration_tests/test_langchain.py
vllm_mlx/_integration_tests/test_librechat_docker.py
vllm_mlx/_integration_tests/test_openwebui.py
vllm_mlx/_integration_tests/test_pydantic_ai_full.py
vllm_mlx/_integration_tests/test_smolagents_full.py
vllm_mlx/agents/__init__.py
vllm_mlx/agents/adapter.py
vllm_mlx/agents/base.py
vllm_mlx/agents/testing.py
vllm_mlx/agents/profiles/aider.yaml
vllm_mlx/agents/profiles/codex.yaml
vllm_mlx/agents/profiles/hermes.yaml
vllm_mlx/agents/profiles/kilo-code.yaml
vllm_mlx/agents/profiles/langchain.yaml
vllm_mlx/agents/profiles/opencode.yaml
vllm_mlx/agents/profiles/openhands.yaml
vllm_mlx/agents/profiles/pydanticai.yaml
vllm_mlx/agents/profiles/qwen-code.yaml
vllm_mlx/agents/profiles/smolagents.yaml
vllm_mlx/api/__init__.py
vllm_mlx/api/anthropic_adapter.py
vllm_mlx/api/anthropic_models.py
vllm_mlx/api/constants.py
vllm_mlx/api/guided.py
vllm_mlx/api/harmony_tools.py
vllm_mlx/api/models.py
vllm_mlx/api/response_format_metrics.py
vllm_mlx/api/responses_adapter.py
vllm_mlx/api/responses_models.py
vllm_mlx/api/streaming.py
vllm_mlx/api/strict_json_schema.py
vllm_mlx/api/tool_calling.py
vllm_mlx/api/tool_logits.py
vllm_mlx/api/utils.py
vllm_mlx/cache/__init__.py
vllm_mlx/cache/protocol.py
vllm_mlx/config/__init__.py
vllm_mlx/config/server_config.py
vllm_mlx/domain/__init__.py
vllm_mlx/domain/events.py
vllm_mlx/engine/__init__.py
vllm_mlx/engine/base.py
vllm_mlx/engine/batched.py
vllm_mlx/kernels/__init__.py
vllm_mlx/kernels/turboquant_fused.py
vllm_mlx/launch/__init__.py
vllm_mlx/launch/_common.py
vllm_mlx/launch/claude_code.py
vllm_mlx/launch/cli.py
vllm_mlx/launch/cline.py
vllm_mlx/launch/continue_dev.py
vllm_mlx/launch/cursor.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/middleware/__init__.py
vllm_mlx/middleware/auth.py
vllm_mlx/middleware/body_depth.py
vllm_mlx/middleware/body_size.py
vllm_mlx/middleware/exception_handlers.py
vllm_mlx/middleware/probe_fastpath.py
vllm_mlx/models/__init__.py
vllm_mlx/patches/__init__.py
vllm_mlx/patches/deepseek_v32_indexer_gate.py
vllm_mlx/patches/qwen3_next_mtp.py
vllm_mlx/reasoning/__init__.py
vllm_mlx/reasoning/base.py
vllm_mlx/reasoning/harmony_stop.py
vllm_mlx/reasoning/qwen3_parser.py
vllm_mlx/reasoning/think_parser.py
vllm_mlx/routes/__init__.py
vllm_mlx/routes/anthropic.py
vllm_mlx/routes/cache.py
vllm_mlx/routes/chat.py
vllm_mlx/routes/completions.py
vllm_mlx/routes/health.py
vllm_mlx/routes/mcp_routes.py
vllm_mlx/routes/metrics.py
vllm_mlx/routes/models.py
vllm_mlx/routes/responses.py
vllm_mlx/runtime/__init__.py
vllm_mlx/runtime/cache.py
vllm_mlx/runtime/diffusion_lane.py
vllm_mlx/runtime/disk_kv_checkpoint.py
vllm_mlx/runtime/model_registry.py
vllm_mlx/runtime/ubc_evict.py
vllm_mlx/service/__init__.py
vllm_mlx/service/helpers.py
vllm_mlx/service/postprocessor.py
vllm_mlx/spec_decode/__init__.py
vllm_mlx/spec_decode/config.py
vllm_mlx/spec_decode/registry.py
vllm_mlx/spec_decode/dflash/__init__.py
vllm_mlx/spec_decode/dflash/accept_counter.py
vllm_mlx/spec_decode/dflash/detect.py
vllm_mlx/spec_decode/dflash/drafter.py
vllm_mlx/spec_decode/dflash/drafter_registry.py
vllm_mlx/spec_decode/dflash/generator.py
vllm_mlx/spec_decode/dflash/verifier.py
vllm_mlx/spec_decode/mtp/__init__.py
vllm_mlx/spec_decode/mtp/accept_counter.py
vllm_mlx/spec_decode/mtp/cache_patch.py
vllm_mlx/spec_decode/mtp/detect.py
vllm_mlx/spec_decode/mtp/dispatch.py
vllm_mlx/spec_decode/mtp/draft_k_controller_v2.py
vllm_mlx/spec_decode/mtp/gemma4_inject.py
vllm_mlx/spec_decode/mtp/generator.py
vllm_mlx/spec_decode/mtp/head.py
vllm_mlx/spec_decode/mtp/qwen3_5_inject.py
vllm_mlx/speculative/__init__.py
vllm_mlx/speculative/prompt_lookup.py
vllm_mlx/speculative/suffix_decoding.py
vllm_mlx/speculative/ddtree/__init__.py
vllm_mlx/speculative/ddtree/eligibility.py
vllm_mlx/speculative/ddtree/runtime.py
vllm_mlx/speculative/ddtree/server.py
vllm_mlx/speculative/dflash/__init__.py
vllm_mlx/speculative/dflash/eligibility.py
vllm_mlx/speculative/dflash/runtime.py
vllm_mlx/speculative/dflash/server.py
vllm_mlx/telemetry/__init__.py
vllm_mlx/telemetry/consent.py
vllm_mlx/telemetry/emit.py
vllm_mlx/telemetry/queue.py
vllm_mlx/telemetry/redact.py
vllm_mlx/telemetry/schema.py
vllm_mlx/telemetry/state.py
vllm_mlx/telemetry/transport.py
vllm_mlx/tool_parsers/__init__.py
vllm_mlx/tool_parsers/abstract_tool_parser.py
vllm_mlx/tool_parsers/hermes_tool_parser.py
vllm_mlx/tool_parsers/qwen_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/generation_config.py
vllm_mlx/utils/json_depth.py
vllm_mlx/utils/mamba_cache.py
vllm_mlx/utils/tokenizer.py