LICENSE
README.md
pyproject.toml
dflash_mlx/__init__.py
dflash_mlx/artifacts.py
dflash_mlx/benchmark.py
dflash_mlx/benchmark_report.py
dflash_mlx/benchmark_suites.py
dflash_mlx/cli.py
dflash_mlx/diagnostics.py
dflash_mlx/doctor.py
dflash_mlx/draft_backend.py
dflash_mlx/generate.py
dflash_mlx/internal_debug.py
dflash_mlx/kernels.py
dflash_mlx/metal_limits.py
dflash_mlx/model.py
dflash_mlx/recurrent_rollback_cache.py
dflash_mlx/serve.py
dflash_mlx/verify_linear.py
dflash_mlx/verify_qmm.py
dflash_mlx.egg-info/PKG-INFO
dflash_mlx.egg-info/SOURCES.txt
dflash_mlx.egg-info/dependency_links.txt
dflash_mlx.egg-info/entry_points.txt
dflash_mlx.egg-info/requires.txt
dflash_mlx.egg-info/top_level.txt
dflash_mlx/cache/__init__.py
dflash_mlx/cache/codecs.py
dflash_mlx/cache/fingerprints.py
dflash_mlx/cache/manager.py
dflash_mlx/cache/prefix_l1.py
dflash_mlx/cache/prefix_l2.py
dflash_mlx/cache/snapshot.py
dflash_mlx/cache/snapshot_service.py
dflash_mlx/cache/store.py
dflash_mlx/engine/__init__.py
dflash_mlx/engine/acceptance.py
dflash_mlx/engine/config.py
dflash_mlx/engine/copyspec.py
dflash_mlx/engine/ddtree.py
dflash_mlx/engine/events.py
dflash_mlx/engine/fallback.py
dflash_mlx/engine/gqa_sdpa.py
dflash_mlx/engine/memory_waterfall.py
dflash_mlx/engine/prefill.py
dflash_mlx/engine/sampling.py
dflash_mlx/engine/spec_epoch.py
dflash_mlx/engine/target_features.py
dflash_mlx/engine/target_gemma4.py
dflash_mlx/engine/target_ops.py
dflash_mlx/engine/target_qwen_gdn.py
dflash_mlx/observability/__init__.py
dflash_mlx/observability/cache.py
dflash_mlx/observability/memory.py
dflash_mlx/observability/writer.py
dflash_mlx/runtime/__init__.py
dflash_mlx/runtime/bundle.py
dflash_mlx/runtime/chip_detect.py
dflash_mlx/runtime/config.py
dflash_mlx/runtime/context.py
dflash_mlx/runtime/loading.py
dflash_mlx/runtime/registry.py
dflash_mlx/server/__init__.py
dflash_mlx/server/config.py
dflash_mlx/server/metrics.py
dflash_mlx/server/model_provider.py
dflash_mlx/server/prefix_cache_flow.py
dflash_mlx/server/prefix_cache_manager.py
dflash_mlx/server/protocol.py
dflash_mlx/server/request_loop.py
dflash_mlx/server/responses_adapter.py
dflash_mlx/server/runtime.py
dflash_mlx/server/tool_calls.py
tests/test_artifacts.py
tests/test_bench_agentic_trace.py
tests/test_bench_prefix_cache_survival_gate.py
tests/test_benchmark_cli.py
tests/test_cli_config.py
tests/test_context_grid.py
tests/test_copyspec.py
tests/test_ddtree.py
tests/test_dflash_swa_mask.py
tests/test_doctor_cli.py
tests/test_engine_acceptance.py
tests/test_engine_prefill_helpers.py
tests/test_engine_rollback.py
tests/test_gated_delta_tree_kernel.py
tests/test_gemma4_draft.py
tests/test_generate_cli.py
tests/test_memory_waterfall.py
tests/test_observability_writer.py
tests/test_old_apple_chip_policy.py
tests/test_prefill_step_size_runtime.py
tests/test_prefix_cache.py
tests/test_prefix_cache_bench_helpers.py
tests/test_prefix_cache_integration.py
tests/test_prefix_l2.py
tests/test_responses_adapter.py
tests/test_root_cli.py
tests/test_runtime_bundle.py
tests/test_runtime_verify_config.py
tests/test_sdpa_parity.py
tests/test_serve_state_machine.py
tests/test_server_metrics.py
tests/test_server_request_loop.py
tests/test_server_tool_calls.py
tests/test_target_fa_window.py
tests/test_target_feature_store.py
tests/test_target_gemma4_cache.py
tests/test_target_gemma4_real.py
tests/test_target_ops.py
tests/test_target_qwen_gdn_real.py
tests/test_target_qwen_tree.py
tests/test_verify_linear_parity.py
tests/test_verify_qmm_parity.py