LICENSE
README.md
pyproject.toml
inference_perf/__init__.py
inference_perf/main.py
inference_perf.egg-info/PKG-INFO
inference_perf.egg-info/SOURCES.txt
inference_perf.egg-info/dependency_links.txt
inference_perf.egg-info/entry_points.txt
inference_perf.egg-info/requires.txt
inference_perf.egg-info/top_level.txt
inference_perf/analysis/__init__.py
inference_perf/analysis/analyze.py
inference_perf/apis/__init__.py
inference_perf/apis/anthropic_messages.py
inference_perf/apis/base.py
inference_perf/apis/chat.py
inference_perf/apis/completion.py
inference_perf/apis/streaming_parser.py
inference_perf/apis/user_session.py
inference_perf/assets/shakespeare.txt
inference_perf/circuit_breaker/__init__.py
inference_perf/circuit_breaker/base.py
inference_perf/circuit_breaker/config.py
inference_perf/circuit_breaker/simple_breaker.py
inference_perf/circuit_breaker/triggers/__init__.py
inference_perf/circuit_breaker/triggers/base.py
inference_perf/circuit_breaker/triggers/config.py
inference_perf/circuit_breaker/triggers/consecutive.py
inference_perf/circuit_breaker/triggers/rate_over_window.py
inference_perf/client/filestorage/__init__.py
inference_perf/client/filestorage/base.py
inference_perf/client/filestorage/gcs.py
inference_perf/client/filestorage/local.py
inference_perf/client/filestorage/s3.py
inference_perf/client/modelserver/__init__.py
inference_perf/client/modelserver/base.py
inference_perf/client/modelserver/mock_client.py
inference_perf/client/modelserver/openai_client.py
inference_perf/client/modelserver/otel_instrumentation.py
inference_perf/client/modelserver/sglang_client.py
inference_perf/client/modelserver/tgi_client.py
inference_perf/client/modelserver/vllm_client.py
inference_perf/client/server_metrics/__init__.py
inference_perf/client/server_metrics/base.py
inference_perf/client/server_metrics/mock_client.py
inference_perf/client/server_metrics/prometheus_client/__init__.py
inference_perf/client/server_metrics/prometheus_client/base.py
inference_perf/client/server_metrics/prometheus_client/google_managed_prometheus_client.py
inference_perf/config/__init__.py
inference_perf/config/common.py
inference_perf/config/config.py
inference_perf/config/apis/__init__.py
inference_perf/config/apis/config.py
inference_perf/config/client/__init__.py
inference_perf/config/client/filestorage/__init__.py
inference_perf/config/client/filestorage/config.py
inference_perf/config/client/modelserver/__init__.py
inference_perf/config/client/modelserver/config.py
inference_perf/config/client/server_metrics/__init__.py
inference_perf/config/client/server_metrics/config.py
inference_perf/config/datagen/__init__.py
inference_perf/config/datagen/config.py
inference_perf/config/datagen/multimodal.py
inference_perf/config/datagen/replay.py
inference_perf/config/datagen/visionarena.py
inference_perf/config/loadgen/__init__.py
inference_perf/config/loadgen/config.py
inference_perf/config/metrics/__init__.py
inference_perf/config/metrics/config.py
inference_perf/config/reportgen/__init__.py
inference_perf/config/reportgen/config.py
inference_perf/config/utils/__init__.py
inference_perf/config/utils/config.py
inference_perf/datagen/__init__.py
inference_perf/datagen/base.py
inference_perf/datagen/cnn_dailymail_datagen.py
inference_perf/datagen/conversation_replay_datagen.py
inference_perf/datagen/datagen_utils.py
inference_perf/datagen/export_replay_graph_to_dot.py
inference_perf/datagen/hf_billsum_datagen.py
inference_perf/datagen/hf_sharegpt_datagen.py
inference_perf/datagen/infinity_instruct_datagen.py
inference_perf/datagen/mock_datagen.py
inference_perf/datagen/multimodal_datagen.py
inference_perf/datagen/multimodal_sampling.py
inference_perf/datagen/otel_trace_replay_datagen.py
inference_perf/datagen/otel_trace_to_replay_graph.py
inference_perf/datagen/otel_trace_utils.py
inference_perf/datagen/random_datagen.py
inference_perf/datagen/replay_graph_session_datagen.py
inference_perf/datagen/replay_graph_types.py
inference_perf/datagen/shared_prefix_datagen.py
inference_perf/datagen/synthetic_datagen.py
inference_perf/datagen/visionarena_datagen.py
inference_perf/datagen/weka_trace_replay_datagen.py
inference_perf/loadgen/__init__.py
inference_perf/loadgen/load_generator.py
inference_perf/loadgen/load_timer.py
inference_perf/mediagen/__init__.py
inference_perf/mediagen/pool.py
inference_perf/mediagen/synthesis.py
inference_perf/metrics/__init__.py
inference_perf/metrics/session_collector.py
inference_perf/metrics/request_collector/__init__.py
inference_perf/metrics/request_collector/base.py
inference_perf/metrics/request_collector/local.py
inference_perf/metrics/request_collector/multiprocess.py
inference_perf/observability/__init__.py
inference_perf/observability/logging/__init__.py
inference_perf/observability/metrics/__init__.py
inference_perf/observability/metrics/prometheus.py
inference_perf/payloads/__init__.py
inference_perf/payloads/media_base.py
inference_perf/payloads/audio/__init__.py
inference_perf/payloads/audio/metrics.py
inference_perf/payloads/audio/spec/__init__.py
inference_perf/payloads/audio/spec/base.py
inference_perf/payloads/audio/spec/local.py
inference_perf/payloads/audio/spec/pre_encoded.py
inference_perf/payloads/audio/spec/remote.py
inference_perf/payloads/audio/spec/synthetic.py
inference_perf/payloads/image/__init__.py
inference_perf/payloads/image/metrics.py
inference_perf/payloads/image/spec/__init__.py
inference_perf/payloads/image/spec/base.py
inference_perf/payloads/image/spec/local.py
inference_perf/payloads/image/spec/pre_encoded.py
inference_perf/payloads/image/spec/remote.py
inference_perf/payloads/image/spec/synthetic.py
inference_perf/payloads/text/__init__.py
inference_perf/payloads/text/metrics.py
inference_perf/payloads/video/__init__.py
inference_perf/payloads/video/metrics.py
inference_perf/payloads/video/spec/__init__.py
inference_perf/payloads/video/spec/base.py
inference_perf/payloads/video/spec/local.py
inference_perf/payloads/video/spec/pre_encoded_frames.py
inference_perf/payloads/video/spec/remote.py
inference_perf/payloads/video/spec/synthetic_frames.py
inference_perf/payloads/video/spec/synthetic_mp4.py
inference_perf/reportgen/__init__.py
inference_perf/reportgen/base.py
inference_perf/utils/__init__.py
inference_perf/utils/cli_parser.py
inference_perf/utils/cli_summary.py
inference_perf/utils/custom_tokenizer.py
inference_perf/utils/report_file.py
inference_perf/utils/request_queue.py
inference_perf/utils/trace_reader.py
inference_perf/utils/numeric/__init__.py
inference_perf/utils/numeric/distribution/__init__.py
inference_perf/utils/numeric/distribution/utils.py
tests/test_config.py
tests/test_conversation_replay_datagen.py
tests/test_logger.py
tests/test_multitenant_loadgen.py
tests/test_otel_instrumentation.py
tests/test_otel_replay_datagen.py
tests/test_otel_trace_to_replay_graph.py
tests/test_otel_trace_utils.py
tests/test_output_len_special_tokens.py
tests/test_reasoning_output_support.py
tests/test_requirements.py
tests/test_streaming_multi_token_chunks.py
tests/test_streaming_response_order.py
tests/test_tool_call_capture.py
tests/test_trace_replay.py
tests/test_weka_replay_datagen.py