LICENSE
PYPI_README.md
README.md
pyproject.toml
mlx_flash.egg-info/PKG-INFO
mlx_flash.egg-info/SOURCES.txt
mlx_flash.egg-info/dependency_links.txt
mlx_flash.egg-info/entry_points.txt
mlx_flash.egg-info/requires.txt
mlx_flash.egg-info/top_level.txt
mlx_flash_compress/__init__.py
mlx_flash_compress/__main__.py
mlx_flash_compress/advanced_prefetch.py
mlx_flash_compress/bench.py
mlx_flash_compress/bench_e2e.py
mlx_flash_compress/bench_final.py
mlx_flash_compress/bench_gemma4.py
mlx_flash_compress/bench_memory_pressure.py
mlx_flash_compress/bench_real.py
mlx_flash_compress/bit_parity.py
mlx_flash_compress/cache.py
mlx_flash_compress/cached_inference.py
mlx_flash_compress/chat.py
mlx_flash_compress/compression.py
mlx_flash_compress/compression_native.py
mlx_flash_compress/config.py
mlx_flash_compress/continuous_batching.py
mlx_flash_compress/ddtree.py
mlx_flash_compress/demo_warmup.py
mlx_flash_compress/dflash.py
mlx_flash_compress/dflash_model.py
mlx_flash_compress/dflash_profile.py
mlx_flash_compress/distributed_experts.py
mlx_flash_compress/eagle3.py
mlx_flash_compress/engine.py
mlx_flash_compress/entropy_coding.py
mlx_flash_compress/expert_merging.py
mlx_flash_compress/expert_pruning.py
mlx_flash_compress/expert_streaming.py
mlx_flash_compress/fast_cache_bindings.py
mlx_flash_compress/hardware.py
mlx_flash_compress/hf_calculator.py
mlx_flash_compress/kv_cache_sharing.py
mlx_flash_compress/kv_compression.py
mlx_flash_compress/layer_quantization.py
mlx_flash_compress/layerskip.py
mlx_flash_compress/lcp_cache.py
mlx_flash_compress/log_config.py
mlx_flash_compress/matformer.py
mlx_flash_compress/mcp_server.py
mlx_flash_compress/mcp_tools.py
mlx_flash_compress/memory_manager.py
mlx_flash_compress/mixed_precision.py
mlx_flash_compress/mlx_lm_patch.py
mlx_flash_compress/model_browser.py
mlx_flash_compress/ollama_compat.py
mlx_flash_compress/page_cache.py
mlx_flash_compress/pipeline.py
mlx_flash_compress/quantized_kv_cache.py
mlx_flash_compress/router_hook.py
mlx_flash_compress/run.py
mlx_flash_compress/rust_bridge.py
mlx_flash_compress/sequoia.py
mlx_flash_compress/serve.py
mlx_flash_compress/shared_expert_pinning.py
mlx_flash_compress/smart_eviction.py
mlx_flash_compress/speculative_experts.py
mlx_flash_compress/ssd_protection.py
mlx_flash_compress/streaming_llm.py
mlx_flash_compress/task_profiler.py
mlx_flash_compress/tier_optimizer.py
mlx_flash_compress/vertical_split.py
mlx_flash_compress/vllm_integration.py
mlx_flash_compress/web_search.py
mlx_flash_compress/kernels/__init__.py
mlx_flash_compress/kernels/loader.py
mlx_flash_compress/kernels/ops.py
tests/test_advanced_prefetch.py
tests/test_bit_parity.py
tests/test_cache.py
tests/test_cached_inference.py
tests/test_chat_auto_select.py
tests/test_compression.py
tests/test_config_hw_ssd.py
tests/test_continuous_batching.py
tests/test_ddtree.py
tests/test_demo_warmup.py
tests/test_dflash_ddtree.py
tests/test_dflash_model.py
tests/test_dflash_profile.py
tests/test_distributed_kv_calc.py
tests/test_eagle3.py
tests/test_entropy_coding.py
tests/test_expert_merging.py
tests/test_expert_pruning.py
tests/test_expert_streaming.py
tests/test_imports.py
tests/test_integration.py
tests/test_kernel_ops.py
tests/test_kernels.py
tests/test_kv_compression.py
tests/test_layer_quantization.py
tests/test_layerskip.py
tests/test_lcp_cache.py
tests/test_log_config.py
tests/test_matformer.py
tests/test_mcp_tools.py
tests/test_memory_manager_hints.py
tests/test_mlx_lm_patch.py
tests/test_multi_precision.py
tests/test_ollama_compat.py
tests/test_page_cache.py
tests/test_pipeline.py
tests/test_profiler_memory.py
tests/test_quantized_kv_cache.py
tests/test_rust_bridge.py
tests/test_sequoia.py
tests/test_serve.py
tests/test_shared_expert_pinning.py
tests/test_speculative_experts.py
tests/test_streaming_llm.py
tests/test_vertical_split.py
tests/test_vllm_integration.py
tests/test_web_search.py