LICENSE
README.md
pyproject.toml
setup.py
src/kvboost/__init__.py
src/kvboost/batch.py
src/kvboost/cache_manager.py
src/kvboost/cacheblend.py
src/kvboost/chunk_registry.py
src/kvboost/compat.py
src/kvboost/disk_tier.py
src/kvboost/engine.py
src/kvboost/flash_attn_ext.py
src/kvboost/kv_quantize.py
src/kvboost/models.py
src/kvboost/oom_recovery.py
src/kvboost/prompt_assembler.py
src/kvboost/py.typed
src/kvboost/selective_recompute.py
src/kvboost.egg-info/PKG-INFO
src/kvboost.egg-info/SOURCES.txt
src/kvboost.egg-info/dependency_links.txt
src/kvboost.egg-info/entry_points.txt
src/kvboost.egg-info/requires.txt
src/kvboost.egg-info/top_level.txt
src/kvboost/cpu_paged/__init__.py
src/kvboost/cpu_paged/block_allocator.py
src/kvboost/cpu_paged/chunk_to_blocks.py
src/kvboost/cpu_paged/cpu_engine.py
src/kvboost/cpu_paged/paged_attn_cpu.py
src/kvboost/server/__init__.py
src/kvboost/server/__main__.py
src/kvboost/server/app.py
src/kvboost/server/batch_queue.py
src/kvboost/server/engine_worker.py
src/kvboost/server/schema.py
src/kvboost/server/tool_parsers.py
src/kvboost/speculative/__init__.py
src/kvboost/speculative/bridge.py
src/kvboost/speculative/config.py
src/kvboost/speculative/draft.py
src/kvboost/speculative/engine.py
src/kvboost/speculative/rollback.py
src/kvboost/speculative/sampler.py
src/kvboost/speculative/stats.py
src/kvboost/speculative/verifier.py
src/kvboost/streaming/__init__.py
src/kvboost/streaming/analyze_profile.py
src/kvboost/streaming/awq_loader.py
src/kvboost/streaming/config.py
src/kvboost/streaming/demo_compare_mlx.py
src/kvboost/streaming/demo_full_resident_3b.py
src/kvboost/streaming/demo_mps_token_by_token.py
src/kvboost/streaming/demo_partial_8b.py
src/kvboost/streaming/demo_speculative.py
src/kvboost/streaming/loader.py
src/kvboost/streaming/model_shell.py
src/kvboost/streaming/pinned_pool.py
src/kvboost/streaming/profile.py
src/kvboost/streaming/profile_run.py
src/kvboost/streaming/qkv_proj.py
src/kvboost/streaming/scheduler.py
src/kvboost/streaming/staging.py
src/kvboost/streaming/streaming_sched.py
src/kvboost/streaming/kernels/__init__.py
src/kvboost/streaming/kernels/exllama_awq.py
src/kvboost/streaming/kernels/marlin.py
tests/test_block_allocator_parity.py
tests/test_cpu_paged.py
tests/test_flash_attn.py
tests/test_flash_attn_real_model.py
tests/test_server.py