List of all items
Structs
- binpack::CostModel
- bootstrap::router::RouteAwareSpan
- bootstrap::router::UuidRequestId
- config::Config
- embedder::EmbedPool
- embedder::adaptive_warmup::AdaptiveWarmupConfig
- embedder::jit_guard::TrtJitGuard
- embedder::jit_guard::TrtJitRejection
- embedder::math::SeqLenDistribution
- embedder::model_files::ModelFiles
- embedder::pool::EmbedPool
- embedder::session::GpuSessionConfig
- embedder::trt_cache::paths::TrtCacheInfo
- embedder::trt_warmup::PrewarmStats
- embedder::trt_warmup::runner::ShapeRunResult
- embedder::types::DualEmbedding
- embedder::types::EmbedStats
- embedder::types::ProbeResult
- embedder::types::SparseEmbedding
- embedder::worker::config::WorkerConfig
- embedder::worker::dispatch::DispatchOutcome
- embedder::worker::guard::EmbedRouteContext
- embedder::worker::guard::WorkerGuard
- embedder::worker::startup::StartupOutcome
- gpu_stats::inner::GpuStatsCollector
- handler::common::XHeaders
- logging::PrependBuild
- logging::PrependModule
- models::DenseEmbeddingData
- models::DenseRequest
- models::DenseResponse
- models::DualEmbeddingData
- models::DualRequest
- models::DualResponse
- models::ModelEntry
- models::ModelsResponse
- models::SparseEmbeddingData
- models::SparseRequest
- models::SparseResponse
- models::SparseValues
- models::TextInput
- models::Usage
- probe::cache::ProbeCache
- probe::fit::DataPoint
- state::AppState
- state::TuningInfo
- sysinfo::MemoryReading
Enums
- config::EpSelection
- config::ModelVariant
- embedder::types::EmbedRequest
- embedder::worker::guard::InferenceOutcome
- error::AppError
- state::ProbeStatus
- sysinfo::MemorySource
Functions
- binpack::bin_pack
- bootstrap::budget::compute_workspace_budget
- bootstrap::build_router
- bootstrap::probe_task::spawn_probe_task
- bootstrap::readiness::run_readiness_checks_and_open
- bootstrap::readiness::run_readiness_probe
- bootstrap::router::build_router
- bootstrap::run_readiness_probe
- config::parse_trt_warmup_shapes
- config::resolve_cost_model_override
- config::warn_if_small_batch_coverage_missing
- embedder::adaptive_warmup::drain_rx
- embedder::adaptive_warmup::run_adaptive_warmup_loop
- embedder::adaptive_warmup::spawn_adaptive_warmup
- embedder::adaptive_warmup::wait_for_quiet_window
- embedder::dense::embed_dense
- embedder::dual::embed_both
- embedder::error::ort_err
- embedder::jit_guard::guard_chunks
- embedder::jit_guard::is_trt_shape_rejected
- embedder::math::median_usize
- embedder::math::normalize_l2
- embedder::math::seq_len_distribution
- embedder::math::sparse_maxpool
- embedder::math::sparse_project
- embedder::model_files::download_model_files
- embedder::model_files::is_model_cached
- embedder::pool::await_worker_signal
- embedder::session::execution_providers
- embedder::session::load_models
- embedder::session::load_session
- embedder::sm_detect::detect_sm_for_device
- embedder::sm_detect::parse_compute_capability
- embedder::sparse::embed_sparse
- embedder::tokenize::build_chunk_arrays
- embedder::tokenize::load_tokenizer
- embedder::tokenize::tokenize_no_pad
- embedder::trt_cache::enumerate::count_engine_files
- embedder::trt_cache::enumerate::count_engine_files_for_sm
- embedder::trt_cache::enumerate::engine_basenames_for_sm
- embedder::trt_cache::enumerate::engine_basenames_in_dir_sorted
- embedder::trt_cache::enumerate::engine_files_for_sm
- embedder::trt_cache::enumerate::matches_sm_suffix
- embedder::trt_cache::fsync::fsync_cache_dir
- embedder::trt_cache::inspect::count_cache_entries
- embedder::trt_cache::inspect::ensure_and_inspect
- embedder::trt_cache::inspect::log_cache_state
- embedder::trt_cache::inspect::run_write_probe
- embedder::trt_cache::paths::engine_cache_path
- embedder::trt_cache::paths::timing_cache_path
- embedder::trt_cache::prewarm_log::log_engine_basenames_before_prewarm
- embedder::trt_cache::prewarm_log::log_engine_basenames_before_prewarm_for_sm
- embedder::trt_warmup::coverage_check_shapes
- embedder::trt_warmup::postcondition::prewarm_persistence_postcondition_failed
- embedder::trt_warmup::postcondition::prewarm_persistence_suspicious_undercount
- embedder::trt_warmup::runner::run_warmup_shape
- embedder::trt_warmup::shard_shapes
- embedder::trt_warmup::trt_prewarm
- embedder::worker::dispatch::dispatch_request
- embedder::worker::dispatch::reply_request_load_error
- embedder::worker::guard::adaptive_warmup_non_trt_compile_ms
- embedder::worker::guard::build_shape_guard
- embedder::worker::guard::classify_inference_outcome
- embedder::worker::guard::finalize_embed_route
- embedder::worker::guard::log_client_abandoned_before_dispatch
- embedder::worker::guard::log_guard_rejection
- embedder::worker::guard::next_consecutive_failures
- embedder::worker::guard::should_unload_on_outcome
- embedder::worker::logging::log_if_abandoned_mid_flight
- embedder::worker::prewarm_strict::should_fail_readiness
- embedder::worker::probe::probe_run_dense
- embedder::worker::probe::run_probe_batch
- embedder::worker::propagation::drain_engine_propagation
- embedder::worker::propagation::log_inference_complete
- embedder::worker::run::run_worker
- embedder::worker::startup::detected_sm_for_ep
- embedder::worker::startup::startup_worker
- embedder::worker::trt_retry::embed_with_trt_retry
- embedder::worker::trt_retry::is_trt_engine_build_fatal
- embedder::worker::trt_retry::is_trt_jit_oom
- handler::both::both_embeddings
- handler::both_embeddings
- handler::common::check_ready
- handler::common::collect_x_headers
- handler::common::validate_input
- handler::dense::dense_embeddings
- handler::dense_embeddings
- handler::health
- handler::health::health
- handler::health::health_deep
- handler::health_deep
- handler::models
- handler::models::models
- handler::sparse::sparse_embeddings
- handler::sparse_embeddings
- logging::init
- probe::cache::save_probe_cache
- probe::cache::try_load_probe_cache
- probe::corpus::load_probe_texts
- probe::corpus::synthesize_texts
- probe::fit::fit_cost_model
- probe::runner::run_probe
- probe::validate::validate_max_seq_shape
- run
- sysinfo::cgroup_memory
- sysinfo::cgroup_v2_walk
- sysinfo::count_nvidia_gpus_from_proc
- sysinfo::detect_available_memory
- sysinfo::detect_gpu_count
- sysinfo::env_override
- sysinfo::host_ram
- sysinfo::linux_meminfo_available
- sysinfo::linux_rss
- sysinfo::page_size_bytes
- sysinfo::read_process_rss_bytes
- wait_for_workers_to_exit
- warmup_postcondition_failed
- weights::sparse_linear
Type Aliases
Statics
Constants
- WARMUP_POSTCONDITION_FAILED_EXIT_CODE
- config::DEFAULT_GPU_VRAM_BUDGET_BYTES
- config::DEFAULT_TRT_WARMUP_SHAPES
- config::MODEL_MAX_SEQ
- config::VRAM_WARN_THRESHOLD_BYTES
- embedder::math::SPECIAL_TOKENS
- embedder::model_files::REPO_ID
- embedder::model_files::REPO_REVISION
- embedder::model_files::XENOVA_REPO_ID
- embedder::model_files::XENOVA_REPO_REVISION
- embedder::trt_cache::paths::TRT_ENGINE_SUBDIR
- embedder::trt_cache::paths::TRT_TIMING_SUBDIR
- embedder::trt_warmup::CACHE_HIT_THRESHOLD_MS
- embedder::trt_warmup::postcondition::SUSPICIOUS_UNDERCOUNT_MIN_FRESH
- embedder::types::OS_HEADROOM_BYTES
- embedder::worker::trt_retry::CHUNK_CACHE_HIT_THRESHOLD_MS
- handler::common::MAX_STRING_CHARS
- handler::health::DEEP_HEALTH_CANARY
- handler::health::DEEP_HEALTH_TIMEOUT
- logging::BGE_MODULE
- logging::BUILD_VARIANT
- probe::runner::PROBE_SHAPES