List of all items

Structs

• commands::bench::BenchCommand
• commands::bench_serve::BenchServeCommand
• commands::doctor::DoctorCommand
• commands::embed::EmbedCommand
• commands::list::ListCommand
• commands::pull::PullCommand
• commands::replay_bundle::ReplayBundleCommand
• commands::run::RunCommand
• commands::serve::ServeCommand
• commands::stop::StopCommand
• commands::transcribe::TranscribeCommand
• commands::tts::TtsCommand
• commands::vnext_checkpoint::VNextCheckpointArgs
• commands::vnext_determinism::VNextDeterminismCommand
• config::BenchmarkConfig
• config::CliConfig
• config::ClientConfig
• config::DevConfig
• config::DownloadConfig
• config::ModelCliConfig
• config::RetryConfig
• config::RuntimeCliConfig
• config::ServerCliConfig
• gpu_devices::CudaLayerSplitStage
• gpu_devices::GpuDeviceSelection
• gpu_mem_autosize::AutoSizeResult
• memory_profile::ProcessMemoryObservation
• memory_profile::ProcessMemorySample
• memory_profile::ProcessMemorySampler
• observability_product::ActualMemoryStageObservation
• observability_product::ActualRunFailureObservation
• observability_product::ActualRunObservation
• observability_product::ProductObservabilityConfig
• source_resolver::ProductEngineInput
• source_resolver::ProductSourceArgs
• source_resolver::Resolved

Enums

• commands::SequenceFitPolicyArg
• commands::VNextDiagnosticFaultArg
• commands::bench_serve::BenchHttpConnectionMode
• commands::bench_serve::BenchTargetBackend
• commands::run::OutputFormat
• commands::vnext_determinism::VNextDeterminismScope
• gpu_mem_autosize::AutoSizeProfile
• layer_split_pipeline::LayerSplitPipelineModeArg
• observability_product::ProfileDetailArg
• source_resolver::DownloadPolicy

Functions

• commands::bench::execute
• commands::bench_serve::execute
• commands::doctor::execute
• commands::embed::execute
• commands::embed::load_tokenizer
• commands::list::execute
• commands::pull::execute
• commands::replay_bundle::execute
• commands::run::apply_kv_dtype_override
• commands::run::execute
• commands::run::select_device
• commands::serve::execute
• commands::stop::execute
• commands::transcribe::execute
• commands::transcribe::select_candle_device
• commands::tts::execute
• commands::vnext_determinism::execute
• gpu_devices::even_layer_split_plan_for_layers
• gpu_devices::even_layer_split_stages_for_layers
• gpu_devices::format_layer_split_plan
• gpu_devices::join_gpu_devices
• gpu_devices::parse_gpu_devices
• gpu_devices::resolve_cuda_gpu_devices
• gpu_devices::validate_gpu_devices_exist
• gpu_mem_autosize::apply_auto_size
• gpu_mem_autosize::apply_auto_size_with_profile
• gpu_mem_autosize::auto_size_kv_blocks
• gpu_mem_autosize::auto_size_kv_blocks_with_pool_copies
• layer_split_pipeline::insert_backend_option_from_runtime
• layer_split_pipeline::normalize_layer_split_pipeline_mode
• layer_split_pipeline::push_cli_runtime_entry
• layer_split_pipeline::runtime_layer_split_pipeline_mode
• memory_profile::sample_process_memory
• observability_product::append_actual_serve_memory_stage_observability
• observability_product::default_profile_sample_rate
• observability_product::write_actual_run_failure_observability
• observability_product::write_actual_run_observability
• observability_product::write_actual_serve_startup_observability
• observability_product::write_synthetic_product_observability
• observability_vertical_slice::write_observability_vertical_slice
• runtime_env::materialize_runtime_env_defaults
• runtime_env::materialize_runtime_env_effective
• runtime_env::moe_graph_default_entries
• runtime_env::push_cli_runtime_entry
• runtime_env::push_cli_runtime_usize
• runtime_env::runtime_snapshot_value
• runtime_env::warn_if_moe_graph_needs_unbuilt_vllm_moe
• source_resolver::apply_chat_profile_env
• source_resolver::chat_profile_runtime_entries
• source_resolver::detect_format
• source_resolver::detect_model_family
• source_resolver::detect_moe_arch
• source_resolver::find_cached_gguf
• source_resolver::find_cached_model
• source_resolver::first_success_model_help
• source_resolver::hf_cache_dir
• source_resolver::load_model_chat_template
• source_resolver::load_prepared_product_chat_template
• source_resolver::load_product_chat_template
• source_resolver::looks_like_gguf_path
• source_resolver::metal_gguf_moe_correctness_entries
• source_resolver::prepare_registered_product_model
• source_resolver::prepared_product_source_identity
• source_resolver::public_model_id
• source_resolver::resolve_gguf_alias
• source_resolver::resolve_model_alias
• source_resolver::resolve_model_source
• source_resolver::resolve_model_source_with_product_sources
• source_resolver::serve_profile_runtime_entries
• source_resolver::serve_profile_runtime_entries_for_arch
• source_resolver::tokenizer_sibling_repo
• utils::setup_logging

Constants

• gpu_devices::CUDA_DEVICE_COUNT_KEY
• gpu_devices::GPU_DEVICES_RAW_KEY
• gpu_devices::REQUESTED_GPU_DEVICES_KEY
• gpu_devices::SELECTED_DISTRIBUTED_STRATEGY_KEY
• gpu_devices::SELECTED_GPU_DEVICES_KEY
• gpu_devices::SELECTED_LAYER_SPLIT_PLAN_KEY
• gpu_devices::SELECTED_LAYER_SPLIT_STAGES_KEY
• layer_split_pipeline::LAYER_SPLIT_PIPELINE_MODE_BACKEND_OPTION
• layer_split_pipeline::LAYER_SPLIT_PIPELINE_MODE_KEY
• source_resolver::CUDA_FIRST_SUCCESS_MODEL
• source_resolver::METAL_FIRST_SUCCESS_MODEL