.clang-format
.gitignore
.isort.cfg
.pre-commit-config.yaml
AGENTS.md
CMakeLists.txt
CODE_OF_CONDUCT.md
CONTRIBUTING.md
DCO
LICENSE
MAINTAINERS.md
MANIFEST.in
README.md
SECURITY.md
format.sh
pyproject.toml
setup.py
.buildkite/README.md
.buildkite/pipeline.yml
.buildkite/vllm-integration-tests.yml
.buildkite/cases/comprehensive-cases.txt
.buildkite/cases/integration-cases.txt
.buildkite/configs/async.yaml
.buildkite/configs/dummy.yaml
.buildkite/configs/layerwise.yaml
.buildkite/configs/local_cpu.yaml
.buildkite/configs/local_cpu_mla.yaml
.buildkite/configs/local_cpu_with_v3.yaml
.buildkite/configs/local_disk.yaml
.buildkite/configs/local_disk_with_v3.yaml
.buildkite/configs/multi_device.yaml
.buildkite/configs/p2p.yaml
.buildkite/configs/p2p_with_v3.yaml
.buildkite/configs/pd.yaml
.buildkite/configs/lmcache_configs/local_cpu_mla.yaml
.buildkite/correctness/README.md
.buildkite/correctness/async_request.py
.buildkite/correctness/compare_files.py
.buildkite/correctness/mmlu-test.py
.buildkite/correctness/pipeline.correctness.yml
.buildkite/correctness/pipeline.mmlu.yml
.buildkite/correctness/setup.sh
.buildkite/correctness/sharegpt2openai.py
.buildkite/correctness/summarize-results.py
.buildkite/pipelines/clean.yml
.buildkite/pipelines/comprehensive-tests.yml
.buildkite/pipelines/end-to-end-tests.yml
.buildkite/pipelines/multiprocessing-test.yml
.buildkite/scripts/bare-machine-cleanup.sh
.buildkite/scripts/clean.sh
.buildkite/scripts/end-to-end-test.sh
.buildkite/scripts/gpu_zombie_killer.sh
.buildkite/scripts/multi-round-qa.sh
.buildkite/scripts/pick-free-gpu-amd.sh
.buildkite/scripts/pick-free-gpu.sh
.buildkite/scripts/should-run-comprehensive.sh
.buildkite/scripts/vllm-correctness.sh
.buildkite/scripts/vllm-integration-tests.sh
.buildkite/scripts/multiprocessing-test/README.md
.buildkite/scripts/multiprocessing-test/build-mp-docker-image.sh
.buildkite/scripts/multiprocessing-test/cleanup.sh
.buildkite/scripts/multiprocessing-test/common.sh
.buildkite/scripts/multiprocessing-test/launch-containers.sh
.buildkite/scripts/multiprocessing-test/run-lm-eval.sh
.buildkite/scripts/multiprocessing-test/run-long-doc-qa.sh
.buildkite/scripts/multiprocessing-test/run-mp-test.sh
.buildkite/scripts/multiprocessing-test/run-vllm-bench.sh
.buildkite/scripts/multiprocessing-test/test-launch.sh
.buildkite/scripts/multiprocessing-test/wait-for-vllm.sh
.github/PULL_REQUEST_TEMPLATE.md
.github/dependabot.yml
.github/ISSUE_TEMPLATE/blank_issue.md
.github/ISSUE_TEMPLATE/bug_report.md
.github/ISSUE_TEMPLATE/feature_request.md
.github/actions/free-disk-space/action.yml
.github/workflows/actionlint.dockerfile
.github/workflows/actionlint.yml
.github/workflows/automerge-labeler.yml
.github/workflows/build_doc.yml
.github/workflows/code_quality_checks.yml
.github/workflows/codeql.yml
.github/workflows/nightly_build.yml
.github/workflows/publish.yml
.github/workflows/scorecard.yml
.github/workflows/stale_bot.yml
.github/workflows/test.yml
.github/workflows/matchers/actionlint.json
.github/workflows/matchers/mypy.json
asset/logo.png
benchmarks/long_doc_qa/long_doc_qa.py
benchmarks/long_doc_qa/long_doc_qa_recommender.py
benchmarks/microbenchmark/ttl_lock_benchmark.py
benchmarks/multi_doc_qa/README.md
benchmarks/multi_doc_qa/lmcache.yaml
benchmarks/multi_doc_qa/lmcache_blend.yaml
benchmarks/multi_doc_qa/multi_doc_qa.py
benchmarks/multi_round_qa/README.md
benchmarks/multi_round_qa/data_preprocessing.py
benchmarks/multi_round_qa/multi-round-qa.py
benchmarks/multi_round_qa/prepare_sharegpt_data.sh
benchmarks/multi_round_qa/requirements.txt
benchmarks/multi_round_qa/utils.py
benchmarks/rag/README.md
benchmarks/rag/launch_lmcache.sh
benchmarks/rag/launch_vllm.sh
benchmarks/rag/precompute.py
benchmarks/rag/rag.py
benchmarks/rag/requirements.txt
benchmarks/rag/utils.py
benchmarks/storage_backend_io/README.md
benchmarks/storage_backend_io/storage_backend_io_benchmark.py
benchmarks/ttft-estimator/llama-h100-example.png
benchmarks/ttft-estimator/ttft-estimator.py
csrc/ac_dec.cu
csrc/ac_enc.cu
csrc/cachegen_kernels.cuh
csrc/cal_cdf.cu
csrc/cuda_compat.h
csrc/dispatch_utils.h
csrc/mem_alloc.cpp
csrc/mem_alloc.h
csrc/mem_kernels.cu
csrc/mem_kernels.cuh
csrc/pos_kernels.cu
csrc/pos_kernels.cuh
csrc/pybind.cpp
csrc/utils.cpp
csrc/utils.h
csrc/redis/pybind.cpp
csrc/redis/resp.cpp
csrc/redis/resp.h
csrc/storage_manager/bitmap.cpp
csrc/storage_manager/bitmap.h
csrc/storage_manager/pybind.cpp
csrc/storage_manager/ttl_lock.cpp
csrc/storage_manager/ttl_lock.h
csrc/storage_manager/utils.cpp
csrc/storage_manager/utils.h
docker/Dockerfile
docker/Dockerfile.lightweight
docker/Dockerfile.standalone
docker/README.md
docker/example_build.sh
docker/example_run.sh
docs/Makefile
docs/README.md
docs/make.bat
docs/source/.nojekyll
docs/source/conf.py
docs/source/index.rst
docs/source/_static/basic_codepath.svg
docs/source/_static/custom.css
docs/source/_static/custom.js
docs/source/_static/full_layerwise_diagram.svg
docs/source/_static/kv_cache_calculator.html
docs/source/_static/modelconfig.json
docs/source/_static/scroll.css
docs/source/_templates/custom.html
docs/source/_templates/versioning.html
docs/source/api_reference/configurations.rst
docs/source/api_reference/dynamic_connector.rst
docs/source/api_reference/multimodality.rst
docs/source/api_reference/storage_backends.rst
docs/source/assets/InfiniStore-usage.png
docs/source/assets/lmcache-controller.png
docs/source/assets/lmcache-logo.png
docs/source/assets/lmcache-logo_crop.png
docs/source/assets/mooncake-store-preview.png
docs/source/community/blogs.rst
docs/source/community/meetings.rst
docs/source/controller/freeze_mode.rst
docs/source/controller/index.rst
docs/source/developer_guide/architecture.rst
docs/source/developer_guide/contributing.rst
docs/source/developer_guide/docker_file.rst
docs/source/developer_guide/integration.rst
docs/source/developer_guide/extending_lmcache/index.rst
docs/source/developer_guide/extending_lmcache/remote_storage_plugins.rst
docs/source/developer_guide/extending_lmcache/runtime_plugins.rst
docs/source/developer_guide/extending_lmcache/storage_plugins.rst
docs/source/developer_guide/usage/basic_check.rst
docs/source/developer_guide/usage/index.rst
docs/source/developer_guide/usage/usage_stats_collection.rst
docs/source/disaggregated_prefill/shared_storage.rst
docs/source/disaggregated_prefill/nixl/1p1d.rst
docs/source/disaggregated_prefill/nixl/index.rst
docs/source/disaggregated_prefill/nixl/xpyd.rst
docs/source/getting_started/benchmarking.rst
docs/source/getting_started/faq.rst
docs/source/getting_started/installation.rst
docs/source/getting_started/kv_cache_calculator.rst
docs/source/getting_started/quickstart.rst
docs/source/getting_started/troubleshoot.rst
docs/source/getting_started/quickstart/disaggregated_prefill.rst
docs/source/getting_started/quickstart/index.rst
docs/source/getting_started/quickstart/multimodality.rst
docs/source/getting_started/quickstart/offload_kv_cache.rst
docs/source/getting_started/quickstart/share_kv_cache.rst
docs/source/getting_started/quickstart/standalone_starter.rst
docs/source/internal_api_server/common_apis.rst
docs/source/internal_api_server/controller_apis.rst
docs/source/internal_api_server/dynamic_backend_management.rst
docs/source/internal_api_server/internal_api_server.rst
docs/source/internal_api_server/vllm_apis.rst
docs/source/kv_cache/async_loading.rst
docs/source/kv_cache/caching_policies.rst
docs/source/kv_cache/multiprocess_mode.rst
docs/source/kv_cache/p2p_sharing.rst
docs/source/kv_cache/storage_backends/cpu_ram.rst
docs/source/kv_cache/storage_backends/custom_backend.rst
docs/source/kv_cache/storage_backends/eic.rst
docs/source/kv_cache/storage_backends/gds.rst
docs/source/kv_cache/storage_backends/index.rst
docs/source/kv_cache/storage_backends/infinistore.rst
docs/source/kv_cache/storage_backends/local_storage.rst
docs/source/kv_cache/storage_backends/mock.rst
docs/source/kv_cache/storage_backends/mooncake.rst
docs/source/kv_cache/storage_backends/nixl.rst
docs/source/kv_cache/storage_backends/redis.rst
docs/source/kv_cache/storage_backends/s3.rst
docs/source/kv_cache/storage_backends/sagemaker_hyperpod.rst
docs/source/kv_cache/storage_backends/valkey.rst
docs/source/kv_cache/storage_backends/weka.rst
docs/source/kv_cache_management/check_finish.rst
docs/source/kv_cache_management/clear.rst
docs/source/kv_cache_management/compress.rst
docs/source/kv_cache_management/health.rst
docs/source/kv_cache_management/index.rst
docs/source/kv_cache_management/lookup.rst
docs/source/kv_cache_management/move.rst
docs/source/kv_cache_management/pin.rst
docs/source/kv_cache_management/query_worker_info.rst
docs/source/kv_cache_optimizations/blending.rst
docs/source/kv_cache_optimizations/layerwise.rst
docs/source/kv_cache_optimizations/compression/cachegen.rst
docs/source/kv_cache_optimizations/compression/index.rst
docs/source/production/docker_deployment.rst
docs/source/production/kubernetes_deployment.rst
docs/source/production/kv_cache_events.rst
docs/source/production/performance_tuning.rst
docs/source/production/observability/chunk_statistics.rst
docs/source/production/observability/frontend.rst
docs/source/production/observability/health_monitor.rst
docs/source/production/observability/index.rst
docs/source/production/observability/internal_api_server.rst
docs/source/production/observability/metrics.rst
docs/source/production/observability/periodic_thread_api.rst
docs/source/production/observability/vllm_endpoint.rst
examples/agents/prefix_analysis.py
examples/agents/requirements.txt
examples/basic_check/README.md
examples/basic_check/example_config.yaml
examples/blend_kv/README.md
examples/blend_kv/batched_kv.py
examples/blend_kv/batched_tp_kv.py
examples/blend_kv/blend_kv.py
examples/blend_kv/chunk1.txt
examples/blend_kv/chunk2.txt
examples/blend_kv/example_blending.yaml
examples/blend_kv/online_kv.py
examples/blend_kv/tp_kv.py
examples/blend_kv_v1/README.md
examples/blend_kv_v1/blend.py
examples/cache_controller/README.md
examples/cache_controller/clear/README.md
examples/cache_controller/clear/example.yaml
examples/cache_controller/compress/README.md
examples/cache_controller/compress/example.yaml
examples/cache_controller/health/README.md
examples/cache_controller/health/example.yaml
examples/cache_controller/lookup/README.md
examples/cache_controller/lookup/example.yaml
examples/cache_controller/move/README.md
examples/cache_controller/move/instance1.yaml
examples/cache_controller/move/instance2.yaml
examples/cache_controller/pin/README.md
examples/cache_controller/pin/example.yaml
examples/cache_interface/README.md
examples/cache_interface/example.yaml
examples/cache_with_configs/README.md
examples/cache_with_configs/example.yaml
examples/chunk_statistics/README.md
examples/chunk_statistics/analyze_chunk_hashes.py
examples/chunk_statistics/auto_stop.yaml
examples/chunk_statistics/file_hash.yaml
examples/chunk_statistics/memory_bloom_filter.yaml
examples/disagg_prefill/README.md
examples/disagg_prefill/disagg_proxy_server.py
examples/disagg_prefill/1p1d/README.md
examples/disagg_prefill/1p1d/disagg_example_1p1d.sh
examples/disagg_prefill/1p1d/disagg_vllm_launcher.sh
examples/disagg_prefill/1p1d/configs/lmcache-decoder-config.yaml
examples/disagg_prefill/1p1d/configs/lmcache-prefiller-config.yaml
examples/disagg_prefill/xpyd/README.md
examples/disagg_prefill/xpyd/disagg_example_xpyd.sh
examples/disagg_prefill/xpyd/disagg_vllm_launcher.sh
examples/disagg_prefill/xpyd/configs/lmcache-decoder-1-config.yaml
examples/disagg_prefill/xpyd/configs/lmcache-decoder-2-config.yaml
examples/disagg_prefill/xpyd/configs/lmcache-prefiller-config.yaml
examples/disagg_prefill_mp/README.md
examples/disagg_prefill_mp/architecture.png
examples/disagg_prefill_mp/disagg_proxy_server.py
examples/frontend/README.md
examples/frontend/chat_session.py
examples/frontend/example.yaml
examples/frontend/ffmpeg.txt
examples/frontend/frontend.py
examples/kubernetes/health_probe.py
examples/kv_cache_calculator/README.md
examples/kv_cache_calculator/generate_config.py
examples/kv_cache_calculator/kv_cache_calculator.html
examples/kv_cache_calculator/modelconfig.json
examples/kv_cache_calculator/requirement.txt
examples/kv_cache_reuse/README.md
examples/kv_cache_reuse/local_backends/README.md
examples/kv_cache_reuse/local_backends/offload.py
examples/kv_cache_reuse/remote_backends/README.md
examples/kv_cache_reuse/remote_backends/external/README.md
examples/kv_cache_reuse/remote_backends/external/backend_type.yaml
examples/kv_cache_reuse/remote_backends/fs/example.yaml
examples/kv_cache_reuse/remote_backends/infinistore/README.md
examples/kv_cache_reuse/remote_backends/infinistore/backend_type.yaml
examples/kv_cache_reuse/remote_backends/mock/README.md
examples/kv_cache_reuse/remote_backends/mock/example.yaml
examples/kv_cache_reuse/remote_backends/mooncakestore/README.md
examples/kv_cache_reuse/remote_backends/mooncakestore/mooncake.yaml
examples/kv_cache_reuse/remote_backends/resp/README.md
examples/kv_cache_reuse/remote_backends/resp/benchmark_resp_client.py
examples/kv_cache_reuse/remote_backends/resp/resp.yaml
examples/kv_cache_reuse/remote_backends/s3/README.md
examples/kv_cache_reuse/remote_backends/s3/example.yaml
examples/kv_cache_reuse/share_across_instances/README.md
examples/kv_cache_reuse/share_across_instances/centralized_sharing/README.md
examples/kv_cache_reuse/share_across_instances/centralized_sharing/example.yaml
examples/kv_cache_reuse/share_across_instances/p2p_sharing/README.md
examples/kv_cache_reuse/share_across_instances/p2p_sharing/example1.yaml
examples/kv_cache_reuse/share_across_instances/p2p_sharing/example2.yaml
examples/multi_process/lmcache-daemonset.yaml
examples/multi_process/vllm-deployment.yaml
examples/online_session/README.md
examples/online_session/bench_ttft_sweep.sh
examples/online_session/example.yaml
examples/online_session/ffmpeg.txt
examples/online_session/openai_chat_completion_client.py
examples/redis_lookup/README.md
examples/remote_config_server/README.md
examples/remote_config_server/config_server.py
examples/remote_config_server/example.yaml
examples/runtime_plugins/README.md
examples/runtime_plugins/all_plugin.sh
examples/runtime_plugins/scheduler_foo_plugin.py
examples/runtime_plugins/worker_0_test.sh
examples/sgl_integration/README.md
examples/sgl_integration/lmcache_config.yaml
lmcache/__init__.py
lmcache/_version.py
lmcache/config.py
lmcache/connections.py
lmcache/logging.py
lmcache/native_storage_ops.pyi
lmcache/non_cuda_equivalents.py
lmcache/observability.py
lmcache/protocol.py
lmcache/usage_context.py
lmcache/utils.py
lmcache.egg-info/PKG-INFO
lmcache.egg-info/SOURCES.txt
lmcache.egg-info/dependency_links.txt
lmcache.egg-info/entry_points.txt
lmcache.egg-info/requires.txt
lmcache.egg-info/top_level.txt
lmcache/integration/__init__.py
lmcache/integration/request_telemetry/__init__.py
lmcache/integration/request_telemetry/base.py
lmcache/integration/request_telemetry/factory.py
lmcache/integration/request_telemetry/fastapi.py
lmcache/integration/request_telemetry/noop.py
lmcache/integration/sglang/__init__.py
lmcache/integration/sglang/sglang_adapter.py
lmcache/integration/sglang/utils.py
lmcache/integration/vllm/__init__.py
lmcache/integration/vllm/lmcache_connector_v1.py
lmcache/integration/vllm/lmcache_connector_v1_085.py
lmcache/integration/vllm/utils.py
lmcache/integration/vllm/vllm_multi_process_adapter.py
lmcache/integration/vllm/vllm_v1_adapter.py
lmcache/integration/vllm/tests/test_mm_hash_utils.py
lmcache/server/__init__.py
lmcache/server/__main__.py
lmcache/server/server_storage_backend/__init__.py
lmcache/server/server_storage_backend/abstract_backend.py
lmcache/server/server_storage_backend/local_backend.py
lmcache/storage_backend/evictor/__init__.py
lmcache/storage_backend/evictor/base_evictor.py
lmcache/storage_backend/evictor/lru_evictor.py
lmcache/storage_backend/serde/__init__.py
lmcache/storage_backend/serde/cachegen_basics.py
lmcache/storage_backend/serde/cachegen_decoder.py
lmcache/storage_backend/serde/cachegen_encoder.py
lmcache/storage_backend/serde/fast_serde.py
lmcache/storage_backend/serde/safe_serde.py
lmcache/storage_backend/serde/serde.py
lmcache/storage_backend/serde/torch_serde.py
lmcache/tools/controller_benchmark/README.md
lmcache/tools/controller_benchmark/__init__.py
lmcache/tools/controller_benchmark/__main__.py
lmcache/tools/controller_benchmark/benchmark.py
lmcache/tools/controller_benchmark/config.py
lmcache/tools/controller_benchmark/constants.py
lmcache/tools/controller_benchmark/handlers/__init__.py
lmcache/tools/controller_benchmark/handlers/admit.py
lmcache/tools/controller_benchmark/handlers/base.py
lmcache/tools/controller_benchmark/handlers/deregister.py
lmcache/tools/controller_benchmark/handlers/evict.py
lmcache/tools/controller_benchmark/handlers/heartbeat.py
lmcache/tools/controller_benchmark/handlers/p2p_lookup.py
lmcache/tools/controller_benchmark/handlers/register.py
lmcache/v1/__init__.py
lmcache/v1/basic_check.py
lmcache/v1/cache_engine.py
lmcache/v1/cache_interface.py
lmcache/v1/config.py
lmcache/v1/config_base.py
lmcache/v1/event_manager.py
lmcache/v1/kv_layer_groups.py
lmcache/v1/lazy_memory_allocator.py
lmcache/v1/manager.py
lmcache/v1/memory_management.py
lmcache/v1/metadata.py
lmcache/v1/periodic_thread.py
lmcache/v1/pin_monitor.py
lmcache/v1/protocol.py
lmcache/v1/rpc_utils.py
lmcache/v1/system_detection.py
lmcache/v1/token_database.py
lmcache/v1/api_server/__init__.py
lmcache/v1/api_server/__main__.py
lmcache/v1/cache_controller/__init__.py
lmcache/v1/cache_controller/config.py
lmcache/v1/cache_controller/controller_manager.py
lmcache/v1/cache_controller/executor.py
lmcache/v1/cache_controller/full_sync_sender.py
lmcache/v1/cache_controller/locks.py
lmcache/v1/cache_controller/message.py
lmcache/v1/cache_controller/observability.py
lmcache/v1/cache_controller/utils.py
lmcache/v1/cache_controller/worker.py
lmcache/v1/cache_controller/commands/__init__.py
lmcache/v1/cache_controller/commands/base.py
lmcache/v1/cache_controller/commands/full_sync.py
lmcache/v1/cache_controller/controllers/__init__.py
lmcache/v1/cache_controller/controllers/full_sync_tracker.py
lmcache/v1/cache_controller/controllers/kv_controller.py
lmcache/v1/cache_controller/controllers/registration_controller.py
lmcache/v1/cache_controller/frontend/static/index.html
lmcache/v1/cache_controller/frontend/static/css/style.css
lmcache/v1/cache_controller/frontend/static/img/logo.png
lmcache/v1/cache_controller/frontend/static/js/controller_app.js
lmcache/v1/check/__init__.py
lmcache/v1/check/check_mode_gen.py
lmcache/v1/check/check_mode_test_remote.py
lmcache/v1/check/check_mode_test_storage_manager.py
lmcache/v1/check/utils.py
lmcache/v1/compute/__init__.py
lmcache/v1/compute/positional_encoding.py
lmcache/v1/compute/attention/__init__.py
lmcache/v1/compute/attention/abstract.py
lmcache/v1/compute/attention/flash_attn.py
lmcache/v1/compute/attention/flash_infer_sparse.py
lmcache/v1/compute/attention/metadata.py
lmcache/v1/compute/attention/utils.py
lmcache/v1/compute/blend/__init__.py
lmcache/v1/compute/blend/blender.py
lmcache/v1/compute/blend/metadata.py
lmcache/v1/compute/blend/utils.py
lmcache/v1/compute/models/__init__.py
lmcache/v1/compute/models/base.py
lmcache/v1/compute/models/llama.py
lmcache/v1/compute/models/qwen3.py
lmcache/v1/compute/models/utils.py
lmcache/v1/distributed/api.py
lmcache/v1/distributed/config.py
lmcache/v1/distributed/error.py
lmcache/v1/distributed/eviction.py
lmcache/v1/distributed/internal_api.py
lmcache/v1/distributed/l1_manager.py
lmcache/v1/distributed/memory_manager.py
lmcache/v1/distributed/storage_controller.py
lmcache/v1/distributed/storage_manager.py
lmcache/v1/distributed/eviction_policy/__init__.py
lmcache/v1/distributed/eviction_policy/factory.py
lmcache/v1/distributed/eviction_policy/lru.py
lmcache/v1/distributed/l2_adapters/__init__.py
lmcache/v1/distributed/l2_adapters/base.py
lmcache/v1/distributed/l2_adapters/config.py
lmcache/v1/distributed/l2_adapters/mock_l2_adapter.py
lmcache/v1/distributed/storage_controllers/__init__.py
lmcache/v1/distributed/storage_controllers/eviction_controller.py
lmcache/v1/distributed/storage_controllers/prefetch_policy.py
lmcache/v1/distributed/storage_controllers/store_controller.py
lmcache/v1/distributed/storage_controllers/store_policy.py
lmcache/v1/exceptions/__init__.py
lmcache/v1/gpu_connector/__init__.py
lmcache/v1/gpu_connector/gpu_connectors.py
lmcache/v1/gpu_connector/gpu_ops.py
lmcache/v1/gpu_connector/mock_gpu_connector.py
lmcache/v1/gpu_connector/utils.py
lmcache/v1/gpu_connector/xpu_connectors.py
lmcache/v1/health_monitor/__init__.py
lmcache/v1/health_monitor/base.py
lmcache/v1/health_monitor/constants.py
lmcache/v1/health_monitor/checks/__init__.py
lmcache/v1/health_monitor/checks/remote_backend_check.py
lmcache/v1/internal_api_server/__init__.py
lmcache/v1/internal_api_server/api_registry.py
lmcache/v1/internal_api_server/api_server.py
lmcache/v1/internal_api_server/utils.py
lmcache/v1/internal_api_server/common/__init__.py
lmcache/v1/internal_api_server/common/env_api.py
lmcache/v1/internal_api_server/common/loglevel_api.py
lmcache/v1/internal_api_server/common/metrics_api.py
lmcache/v1/internal_api_server/common/periodic_thread_api.py
lmcache/v1/internal_api_server/common/run_script_api.py
lmcache/v1/internal_api_server/common/thread_api.py
lmcache/v1/internal_api_server/controller/__init__.py
lmcache/v1/internal_api_server/controller/key_stats_api.py
lmcache/v1/internal_api_server/controller/worker_info_api.py
lmcache/v1/internal_api_server/vllm/__init__.py
lmcache/v1/internal_api_server/vllm/backend_api.py
lmcache/v1/internal_api_server/vllm/bypass_api.py
lmcache/v1/internal_api_server/vllm/cache_api.py
lmcache/v1/internal_api_server/vllm/chunk_statistics_api.py
lmcache/v1/internal_api_server/vllm/conf_api.py
lmcache/v1/internal_api_server/vllm/freeze_api.py
lmcache/v1/internal_api_server/vllm/hot_cache_api.py
lmcache/v1/internal_api_server/vllm/inference_api.py
lmcache/v1/internal_api_server/vllm/load_fs_chunks_api.py
lmcache/v1/internal_api_server/vllm/lookup_api.py
lmcache/v1/internal_api_server/vllm/version_api.py
lmcache/v1/lookup_client/__init__.py
lmcache/v1/lookup_client/abstract_client.py
lmcache/v1/lookup_client/async_lookup_message.py
lmcache/v1/lookup_client/chunk_statistics_lookup_client.py
lmcache/v1/lookup_client/factory.py
lmcache/v1/lookup_client/hit_limit_lookup_client.py
lmcache/v1/lookup_client/lmcache_async_lookup_client.py
lmcache/v1/lookup_client/lmcache_lookup_client.py
lmcache/v1/lookup_client/lmcache_lookup_client_bypass.py
lmcache/v1/lookup_client/mooncake_lookup_client.py
lmcache/v1/lookup_client/record_strategies/__init__.py
lmcache/v1/lookup_client/record_strategies/base.py
lmcache/v1/lookup_client/record_strategies/file_hash.py
lmcache/v1/lookup_client/record_strategies/memory_bloom_filter.py
lmcache/v1/mp_observability/LOGGER_GUIDE.md
lmcache/v1/mp_observability/METRICS.md
lmcache/v1/mp_observability/config.py
lmcache/v1/mp_observability/prometheus_controller.py
lmcache/v1/mp_observability/logger/integrator_stats_logger.py
lmcache/v1/mp_observability/logger/l1_stats_logger.py
lmcache/v1/mp_observability/logger/l2_stats_logger.py
lmcache/v1/mp_observability/logger/mp_server_logger.py
lmcache/v1/mp_observability/logger/prometheus_logger.py
lmcache/v1/mp_observability/logger/storage_manager_stats_logger.py
lmcache/v1/mp_observability/stats/l1_stats.py
lmcache/v1/mp_observability/stats/mp_server_stats.py
lmcache/v1/mp_observability/stats/storage_manager_stats.py
lmcache/v1/mp_observability/stats/vllm_integrator_stats.py
lmcache/v1/multiprocess/__init__.py
lmcache/v1/multiprocess/blend_server.py
lmcache/v1/multiprocess/custom_types.py
lmcache/v1/multiprocess/futures.py
lmcache/v1/multiprocess/gpu_context.py
lmcache/v1/multiprocess/http_server.py
lmcache/v1/multiprocess/mq.py
lmcache/v1/multiprocess/protocol.py
lmcache/v1/multiprocess/server.py
lmcache/v1/multiprocess/session.py
lmcache/v1/multiprocess/token_hasher.py
lmcache/v1/multiprocess/protocols/README.md
lmcache/v1/multiprocess/protocols/__init__.py
lmcache/v1/multiprocess/protocols/base.py
lmcache/v1/multiprocess/protocols/blend.py
lmcache/v1/multiprocess/protocols/controller.py
lmcache/v1/multiprocess/protocols/debug.py
lmcache/v1/multiprocess/protocols/engine.py
lmcache/v1/offload_server/__init__.py
lmcache/v1/offload_server/abstract_server.py
lmcache/v1/offload_server/message.py
lmcache/v1/offload_server/zmq_server.py
lmcache/v1/plugin/__init__.py
lmcache/v1/plugin/runtime_plugin_launcher.py
lmcache/v1/server/__init__.py
lmcache/v1/server/__main__.py
lmcache/v1/server/utils.py
lmcache/v1/server/storage_backend/__init__.py
lmcache/v1/server/storage_backend/abstract_backend.py
lmcache/v1/server/storage_backend/local_backend.py
lmcache/v1/standalone/__init__.py
lmcache/v1/standalone/__main__.py
lmcache/v1/standalone/manager.py
lmcache/v1/storage_backend/__init__.py
lmcache/v1/storage_backend/abstract_backend.py
lmcache/v1/storage_backend/audit_backend.py
lmcache/v1/storage_backend/batched_message_sender.py
lmcache/v1/storage_backend/gds_backend.py
lmcache/v1/storage_backend/local_cpu_backend.py
lmcache/v1/storage_backend/local_disk_backend.py
lmcache/v1/storage_backend/nixl_storage_backend.py
lmcache/v1/storage_backend/p2p_backend.py
lmcache/v1/storage_backend/pd_backend.py
lmcache/v1/storage_backend/remote_backend.py
lmcache/v1/storage_backend/resp_client.py
lmcache/v1/storage_backend/storage_backend_listener.py
lmcache/v1/storage_backend/storage_manager.py
lmcache/v1/storage_backend/cache_policy/__init__.py
lmcache/v1/storage_backend/cache_policy/base_policy.py
lmcache/v1/storage_backend/cache_policy/fifo.py
lmcache/v1/storage_backend/cache_policy/lfu.py
lmcache/v1/storage_backend/cache_policy/lru.py
lmcache/v1/storage_backend/cache_policy/mru.py
lmcache/v1/storage_backend/connector/__init__.py
lmcache/v1/storage_backend/connector/audit_adapter.py
lmcache/v1/storage_backend/connector/audit_connector.py
lmcache/v1/storage_backend/connector/base_connector.py
lmcache/v1/storage_backend/connector/blackhole_adapter.py
lmcache/v1/storage_backend/connector/blackhole_connector.py
lmcache/v1/storage_backend/connector/eic_adapter.py
lmcache/v1/storage_backend/connector/eic_connector.py
lmcache/v1/storage_backend/connector/external_adapter.py
lmcache/v1/storage_backend/connector/fs_adapter.py
lmcache/v1/storage_backend/connector/fs_connector.py
lmcache/v1/storage_backend/connector/infinistore_adapter.py
lmcache/v1/storage_backend/connector/infinistore_connector.py
lmcache/v1/storage_backend/connector/instrumented_connector.py
lmcache/v1/storage_backend/connector/lm_adapter.py
lmcache/v1/storage_backend/connector/lm_connector.py
lmcache/v1/storage_backend/connector/mock_adapter.py
lmcache/v1/storage_backend/connector/mock_connector.py
lmcache/v1/storage_backend/connector/mooncakestore_adapter.py
lmcache/v1/storage_backend/connector/mooncakestore_connector.py
lmcache/v1/storage_backend/connector/redis_adapter.py
lmcache/v1/storage_backend/connector/redis_connector.py
lmcache/v1/storage_backend/connector/s3_adapter.py
lmcache/v1/storage_backend/connector/s3_connector.py
lmcache/v1/storage_backend/connector/sagemaker_hyperpod_adapter.py
lmcache/v1/storage_backend/connector/sagemaker_hyperpod_connector.py
lmcache/v1/storage_backend/connector/valkey_adapter.py
lmcache/v1/storage_backend/connector/valkey_connector.py
lmcache/v1/storage_backend/job_executor/__init__.py
lmcache/v1/storage_backend/job_executor/base_executor.py
lmcache/v1/storage_backend/job_executor/pq_executor.py
lmcache/v1/storage_backend/naive_serde/__init__.py
lmcache/v1/storage_backend/naive_serde/cachegen_basics.py
lmcache/v1/storage_backend/naive_serde/cachegen_decoder.py
lmcache/v1/storage_backend/naive_serde/cachegen_encoder.py
lmcache/v1/storage_backend/naive_serde/kivi_serde.py
lmcache/v1/storage_backend/naive_serde/naive_serde.py
lmcache/v1/storage_backend/naive_serde/serde.py
lmcache/v1/storage_backend/plugins/rust_raw_block_backend.py
lmcache/v1/transfer_channel/__init__.py
lmcache/v1/transfer_channel/abstract.py
lmcache/v1/transfer_channel/mock_memory_channel.py
lmcache/v1/transfer_channel/nixl_channel.py
lmcache/v1/transfer_channel/py_socket_channel.py
lmcache/v1/transfer_channel/transfer_utils.py
lmcache/v1/utils/__init__.py
lmcache/v1/utils/bloom_filter.py
lmcache/v1/utils/cache_utils.py
requirements/bench.txt
requirements/build.txt
requirements/common.txt
requirements/cuda.txt
requirements/docs.txt
requirements/lint.txt
requirements/test.txt
rust/raw_block/Cargo.toml
rust/raw_block/README.md
rust/raw_block/pyproject.toml
rust/raw_block/src/lib.rs
tests/__init__.py
tests/conftest.py
tests/pytest.ini
tests/test_observability.py
tests/test_protocol.py
tests/test_serde.py
tests/test_utils.py
tests/benchmarks/test_benchmark.py
tests/benchmarks/test_cachegen.py
tests/data/test_creation_from_file/disk.yaml
tests/data/test_creation_from_file/fail.yaml
tests/data/test_creation_from_file/hybrid.yaml
tests/data/test_creation_from_file/local.yaml
tests/data/test_creation_from_file/remote.yaml
tests/disagg/README.md
tests/disagg/test_nixl_cache_engine.py
tests/disagg/test_nixl_channel.py
tests/disagg/test_nixl_storage_backend.py
tests/tools/test_controller_zmq_benchmark.py
tests/v1/__init__.py
tests/v1/test_address_manager.py
tests/v1/test_basic_check.py
tests/v1/test_cache_engine.py
tests/v1/test_cache_interface.py
tests/v1/test_cache_policy.py
tests/v1/test_config.py
tests/v1/test_connector.py
tests/v1/test_connector_discovery.py
tests/v1/test_freeze_mode_integration.py
tests/v1/test_gds.py
tests/v1/test_gpu_connector.py
tests/v1/test_health_monitor.py
tests/v1/test_health_monitor_fallback_recovery.py
tests/v1/test_impl_completeness.py
tests/v1/test_kv_layer_groups_manager.py
tests/v1/test_manager.py
tests/v1/test_mem_kernels.py
tests/v1/test_memory_management.py
tests/v1/test_nixl_storage.py
tests/v1/test_pos_kernels.py
tests/v1/test_remote_metadata.py
tests/v1/test_remote_mla_worker_id_as0.py
tests/v1/test_token_database.py
tests/v1/test_vllm_integration.py
tests/v1/test_vllm_layerwise_wait_for_save.py
tests/v1/utils.py
tests/v1/cache_controller/__init__.py
tests/v1/cache_controller/conftest.py
tests/v1/cache_controller/pytest.ini
tests/v1/cache_controller/test_config.py
tests/v1/cache_controller/test_full_sync.py
tests/v1/cache_controller/test_full_sync_sender.py
tests/v1/cache_controller/test_kv_controller.py
tests/v1/cache_controller/test_locks.py
tests/v1/cache_controller/test_messages.py
tests/v1/cache_controller/test_registration_controller.py
tests/v1/cache_controller/test_registry_tree.py
tests/v1/data/gds.yaml
tests/v1/data/nixl.yaml
tests/v1/data/test_config.yaml
tests/v1/distributed/__init__.py
tests/v1/distributed/conftest.py
tests/v1/distributed/test_distributed_storage_manager.py
tests/v1/distributed/test_l1_manager.py
tests/v1/distributed/test_l1_memory_manager.py
tests/v1/distributed/test_lru_eviction_policy.py
tests/v1/distributed/test_mock_l2_adapter.py
tests/v1/distributed/test_object_key_parallel.py
tests/v1/distributed/test_prefetch_policy.py
tests/v1/distributed/test_store_controller.py
tests/v1/distributed/test_store_policy.py
tests/v1/internal_api_server/test_backend_api.py
tests/v1/internal_api_server/test_cache_clear.py
tests/v1/internal_api_server/test_hot_cache_api.py
tests/v1/internal_api_server/test_kvcache_check_api.py
tests/v1/internal_api_server/test_load_fs_chunks.py
tests/v1/internal_api_server/test_lookup_api.py
tests/v1/internal_api_server/test_run_script.py
tests/v1/internal_api_server/test_worker_info_api.py
tests/v1/internal_api_server/test_scripts/allowed_imports.py
tests/v1/internal_api_server/test_scripts/basic.py
tests/v1/internal_api_server/test_scripts/builtin_functions.py
tests/v1/internal_api_server/test_scripts/default_result.py
tests/v1/internal_api_server/test_scripts/empty_allowed_imports.py
tests/v1/internal_api_server/test_scripts/exception.py
tests/v1/internal_api_server/test_scripts/invalid_module.py
tests/v1/internal_api_server/test_scripts/math_module.py
tests/v1/internal_api_server/test_scripts/multiple_imports.py
tests/v1/internal_api_server/test_scripts/os_module.py
tests/v1/internal_api_server/test_scripts/without_allowed_imports.py
tests/v1/lookup_client/__init__.py
tests/v1/lookup_client/test_chunk_statistics_lookup_client.py
tests/v1/lookup_client/test_lmcache_lookup_client.py
tests/v1/mp_observability/test_l1_stats_logger.py
tests/v1/mp_observability/test_l2_stats_logger.py
tests/v1/mp_observability/test_prometheus_controller.py
tests/v1/mp_observability/test_storage_manager_stats_logger.py
tests/v1/multiprocess/__init__.py
tests/v1/multiprocess/test_blend_server.py
tests/v1/multiprocess/test_cache_server.py
tests/v1/multiprocess/test_custom_types.py
tests/v1/multiprocess/test_futures.py
tests/v1/multiprocess/test_mq.py
tests/v1/multiprocess/test_mq_handler_helpers.py
tests/v1/multiprocess/test_session.py
tests/v1/multiprocess/test_token_hasher.py
tests/v1/native_storage_ops/test_bitmap.py
tests/v1/native_storage_ops/test_pattern_matcher.py
tests/v1/native_storage_ops/test_ttl_lock.py
tests/v1/plugin/test_runtime_plugin_launcher.py
tests/v1/shm_allocator/__init__.py
tests/v1/shm_allocator/shmfile_basic_check.yaml
tests/v1/shm_allocator/shmfile_connector.py
tests/v1/shm_allocator/test_shm_allocator.py
tests/v1/shm_allocator/verify_shmfile_tcp.py
tests/v1/shm_allocator/csrc/.gitignore
tests/v1/shm_allocator/csrc/CMakeLists.txt
tests/v1/shm_allocator/csrc/shm_file_worker.cpp
tests/v1/storage_backend/__init__.py
tests/v1/storage_backend/test_audit_connector.py
tests/v1/storage_backend/test_batched_message_sender.py
tests/v1/storage_backend/test_eic.py
tests/v1/storage_backend/test_fs_connector.py
tests/v1/storage_backend/test_gds_backend.py
tests/v1/storage_backend/test_local_cpu_backend.py
tests/v1/storage_backend/test_local_disk_backend.py
tests/v1/storage_backend/test_p2p_backend_with_controller.py
tests/v1/storage_backend/test_remote_storage_plugin.py
tests/v1/storage_backend/test_resp_connector.py
tests/v1/storage_backend/test_rust_raw_block_backend.py
tests/v1/storage_backend/test_storage_manager.py
tests/v1/storage_backend/test_storage_plugin.py
tools/check_spdx_header.py