.clang-format
.clang-tidy
.gitignore
CMakeLists.txt
CODE_OF_CONDUCT.md
LICENSE
MANIFEST.in
Makefile
README.md
environment-dev.yml
pyproject.toml
requirements-dev.txt
requirements.txt
setup.py
.github/PULL_REQUEST_TEMPLATE.md
.github/workflows/lint.yml
.github/workflows/publish.yml
.vscode/settings.json
assets/batch_size.png
assets/chrome_trace.png
assets/decode_time_execution_plus_preemption_normalized.png
assets/llama70b_Chat1M_ttft_tbt_90_99_2.0_0.2.jpeg
assets/prefill_e2e_time.png
assets/request_e2e_time.png
cmake/utils.cmake
csrc/include/vidur/pybind.h
csrc/include/vidur/config/config.h
csrc/include/vidur/config/config_pybind.h
csrc/include/vidur/entities/batch.h
csrc/include/vidur/entities/entities_pybind.h
csrc/include/vidur/entities/execution_time.h
csrc/include/vidur/entities/kv_parallel_batch.h
csrc/include/vidur/execution_time_predictor/execution_time_predictor.h
csrc/include/vidur/execution_time_predictor/execution_time_predictor_pybind.h
csrc/include/vidur/execution_time_predictor/prediction_keys.h
csrc/vidur/native/pybind.cpp
csrc/vidur/native/config/config.cpp
csrc/vidur/native/config/config_pybind.cpp
csrc/vidur/native/entities/batch.cpp
csrc/vidur/native/entities/entities_pybind.cpp
csrc/vidur/native/entities/execution_time.cpp
csrc/vidur/native/entities/kv_parallel_batch.cpp
csrc/vidur/native/execution_time_predictor/execution_time_predictor.cpp
csrc/vidur/native/execution_time_predictor/execution_time_predictor_pybind.cpp
data/processed_traces/arxiv_summarization_stats_llama2_tokenizer_filtered_v2.csv
data/processed_traces/sharegpt_8k_filtered_stats_llama2_tokenizer.csv
data/processed_traces/splitwise_code.csv
data/processed_traces/splitwise_conv.csv
docs/metrics.md
docs/profiling.md
examples/vidur_cpp/CMakeLists.txt
examples/vidur_cpp/Makefile
examples/vidur_cpp/config_test.cpp
examples/vidur_cpp/cmake/FindVidur.cmake
test/unit/cpp_python_bindings_test.py
vidur/__init__.py
vidur/_version.py
vidur/logger.py
vidur/main.py
vidur/simulator.py
vidur/version.py
vidur.egg-info/PKG-INFO
vidur.egg-info/SOURCES.txt
vidur.egg-info/dependency_links.txt
vidur.egg-info/entry_points.txt
vidur.egg-info/requires.txt
vidur.egg-info/top_level.txt
vidur/cli/data_cli.py
vidur/config/__init__.py
vidur/config/base_fixed_config.py
vidur/config/base_poly_config.py
vidur/config/config.py
vidur/config/device_sku_config.py
vidur/config/flat_dataclass.py
vidur/config/model_config.py
vidur/config/node_sku_config.py
vidur/config/utils.py
vidur/config_optimizer/__init__.py
vidur/config_optimizer/analyzer/__init__.py
vidur/config_optimizer/analyzer/bottleneck_analyzer.py
vidur/config_optimizer/analyzer/bottleneck_cases.py
vidur/config_optimizer/analyzer/constants.py
vidur/config_optimizer/analyzer/generate_pareto_curves.py
vidur/config_optimizer/analyzer/stats_extractor.py
vidur/config_optimizer/analyzer/utils.py
vidur/config_optimizer/analyzer/dashboard/__init__.py
vidur/config_optimizer/analyzer/dashboard/best_config_page.py
vidur/config_optimizer/analyzer/dashboard/config_compare_page.py
vidur/config_optimizer/analyzer/dashboard/cost_analysis_page.py
vidur/config_optimizer/analyzer/dashboard/intro_page.py
vidur/config_optimizer/analyzer/dashboard/main.py
vidur/config_optimizer/analyzer/dashboard/pareto_curve_page.py
vidur/config_optimizer/analyzer/dashboard/search_analysis_page.py
vidur/config_optimizer/analyzer/dashboard/utils.py
vidur/config_optimizer/analyzer/dashboard/assets/favicon.png
vidur/config_optimizer/analyzer/dashboard/assets/index.html
vidur/config_optimizer/analyzer/dashboard/assets/nginx.conf
vidur/config_optimizer/config_explorer/__init__.py
vidur/config_optimizer/config_explorer/capacity_search.py
vidur/config_optimizer/config_explorer/config_explorer.py
vidur/config_optimizer/config_explorer/main.py
vidur/config_optimizer/config_explorer/ray_utils.py
vidur/config_optimizer/config_explorer/config/__init__.py
vidur/config_optimizer/config_explorer/config/config.py
vidur/config_optimizer/config_explorer/config/config.yml
vidur/config_optimizer/config_explorer/config/debug_config.yml
vidur/entities/__init__.py
vidur/entities/base_entity.py
vidur/entities/batch.py
vidur/entities/batch_stage.py
vidur/entities/cluster.py
vidur/entities/execution_time.py
vidur/entities/kv_parallel_batch.py
vidur/entities/kv_parallel_batch_stage.py
vidur/entities/replica.py
vidur/entities/request.py
vidur/events/__init__.py
vidur/events/base_event.py
vidur/events/batch_end_event.py
vidur/events/batch_stage_arrival_event.py
vidur/events/batch_stage_end_event.py
vidur/events/global_schedule_event.py
vidur/events/replica_schedule_event.py
vidur/events/replica_stage_schedule_event.py
vidur/events/request_arrival_event.py
vidur/execution_time_predictor/__init__.py
vidur/execution_time_predictor/base_execution_time_predictor.py
vidur/execution_time_predictor/execution_time_predictor_registry.py
vidur/execution_time_predictor/linear_regression_execution_time_predictor.py
vidur/execution_time_predictor/random_forrest_execution_time_predictor.py
vidur/execution_time_predictor/sklearn_execution_time_predictor.py
vidur/metrics/__init__.py
vidur/metrics/cdf_sketch.py
vidur/metrics/constants.py
vidur/metrics/data_series.py
vidur/metrics/metrics_store.py
vidur/metrics/series_average_meter.py
vidur/profiling/__init__.py
vidur/profiling/attention/__init__.py
vidur/profiling/attention/attention_input.py
vidur/profiling/attention/attention_wrapper.py
vidur/profiling/attention/main.py
vidur/profiling/attention/sequence_proxy.py
vidur/profiling/collectives/__init__.py
vidur/profiling/collectives/benchmark_runner.py
vidur/profiling/collectives/collectives_impl.py
vidur/profiling/collectives/collectives_input.py
vidur/profiling/collectives/collectives_wrapper.py
vidur/profiling/collectives/main.py
vidur/profiling/common/__init__.py
vidur/profiling/common/cuda_timer.py
vidur/profiling/common/model_config.py
vidur/profiling/common/timer_stats_store.py
vidur/profiling/mlp/__init__.py
vidur/profiling/mlp/main.py
vidur/profiling/mlp/mlp_impl.py
vidur/profiling/mlp/mlp_wrapper.py
vidur/profiling/utils/__init__.py
vidur/profiling/utils/record_function_tracer.py
vidur/profiling/utils/singleton.py
vidur/request_generator/__init__.py
vidur/request_generator/base_request_generator.py
vidur/request_generator/base_request_interval_generator.py
vidur/request_generator/base_request_length_generator.py
vidur/request_generator/fixed_request_length_generator.py
vidur/request_generator/gamma_request_interval_generator.py
vidur/request_generator/poisson_request_interval_generator.py
vidur/request_generator/request_generator_registry.py
vidur/request_generator/request_interval_generator_registry.py
vidur/request_generator/request_length_generator_registry.py
vidur/request_generator/static_request_interval_generator.py
vidur/request_generator/synthetic_request_generator.py
vidur/request_generator/trace_replay_request_generator.py
vidur/request_generator/trace_request_interval_generator.py
vidur/request_generator/trace_request_length_generator.py
vidur/request_generator/uniform_request_length_generator.py
vidur/request_generator/zipf_request_length_generator.py
vidur/scheduler/__init__.py
vidur/scheduler/global_scheduler/__init__.py
vidur/scheduler/global_scheduler/base_global_scheduler.py
vidur/scheduler/global_scheduler/global_scheduler_registry.py
vidur/scheduler/global_scheduler/lor_global_scheduler.py
vidur/scheduler/global_scheduler/random_global_scheduler.py
vidur/scheduler/global_scheduler/round_robin_global_scheduler.py
vidur/scheduler/replica_scheduler/__init__.py
vidur/scheduler/replica_scheduler/base_replica_scheduler.py
vidur/scheduler/replica_scheduler/faster_transformer_replica_scheduler.py
vidur/scheduler/replica_scheduler/lightllm_replica_scheduler.py
vidur/scheduler/replica_scheduler/mnemosyne_base_replica_scheduler.py
vidur/scheduler/replica_scheduler/mnemosyne_edf_replica_scheduler.py
vidur/scheduler/replica_scheduler/mnemosyne_fcfs_fixed_chunk_replica_scheduler.py
vidur/scheduler/replica_scheduler/mnemosyne_fcfs_replica_scheduler.py
vidur/scheduler/replica_scheduler/mnemosyne_lrs_replica_scheduler.py
vidur/scheduler/replica_scheduler/mnemosyne_st_replica_scheduler.py
vidur/scheduler/replica_scheduler/orca_replica_scheduler.py
vidur/scheduler/replica_scheduler/replica_scheduler_registry.py
vidur/scheduler/replica_scheduler/sarathi_replica_scheduler.py
vidur/scheduler/replica_scheduler/vllm_replica_scheduler.py
vidur/scheduler/replica_stage_scheduler/__init__.py
vidur/scheduler/replica_stage_scheduler/replica_stage_schduler.py
vidur/scheduler/utils/__init__.py
vidur/scheduler/utils/memory_planner.py
vidur/types/__init__.py
vidur/types/activation_type.py
vidur/types/base_int_enum.py
vidur/types/device_sku_type.py
vidur/types/event_type.py
vidur/types/execution_time_predictor_type.py
vidur/types/global_scheduler_type.py
vidur/types/node_sku_type.py
vidur/types/norm_type.py
vidur/types/replica_scheduler_type.py
vidur/types/request_generator_type.py
vidur/types/request_interval_generator_type.py
vidur/types/request_length_generator_type.py
vidur/utils/__init__.py
vidur/utils/base_registry.py
vidur/utils/event_queue.py
vidur/utils/hf_dataset_utils.py
vidur/utils/mfu_calculator.py
vidur/utils/parallel.py
vidur/utils/param_counter.py
vidur/utils/random.py
vidur/utils/zipf_generator.py