Removed / breaking in @v0.1.803-beta, gone in @v0.1.804-beta
CountAbortedClassstudio/backend/core/inference/llama_cpp.py
GgufLoadIntentClassstudio/backend/core/inference/llama_cpp.py
GgufLoadIntent.__post_init__Methodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackendClassstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend.__init__Methodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._active_gpu_visibility_maskMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._addMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._ambiguous_image_arch_is_pickableMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._amd_apu_wants_unified_memoryMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._amd_smi_hip_id_mapMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._apple_ctx_fitMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._apple_footprint_mibMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._apple_metal_memory_budget_bytesMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._apply_cpu_fallback_stateMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._apply_datacenter_envMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._apply_detected_audioMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._apply_mmproj_cpu_pinMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._apu_ram_shortfall_messageMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._arch_crash_retry_gpu_idsMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._arch_gate_survivorsMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._argv_offloads_every_layerMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._as_cpu_fallback_intentMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._attach_internal_feedback_to_tool_resultMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._auth_headersMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._auto_vulkan_cpu_fallback_eligibleMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._available_system_memory_mibMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._backend_lacks_gpu_libMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._binary_changed_since_launchMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._binary_changed_since_revisionMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._binary_keyMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._binary_revisionMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._binary_ships_no_gpu_backendMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._binary_stampMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._block_textMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._budget_priced_placementMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._build_metadata_eventMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._build_openai_messagesMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._build_speculative_flagsMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._build_windows_path_dirsMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._bundled_hip_symbol_missMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cached_repo_dflash_drafterMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cached_repo_dspark_drafterMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cached_repo_mtp_drafterMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._can_estimate_kvMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cancel_watcherMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cap_ctx_to_per_device_reserveMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cc_atMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cc_bytesMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cc_ctxMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cc_split_extraMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cgroup_available_memory_mibMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._classify_gpu_offloadMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._classify_llama_start_failureMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._classify_macos_loader_failureMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._classify_start_failure_textMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cleanupMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cleanup_cpu_fallback_runtimeMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cleanup_failed_cpu_fallbackMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._clear_device_placement_envMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._clear_manual_placement_envMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._clear_server_pidMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._clear_split_placement_envMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._close_streamed_thinkMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._close_when_cancelledMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cmd_has_gpu_companionMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cmd_has_gpu_device_pinMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._collect_descendantsMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._commit_effective_parallel_slotsMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._compute_buffer_ctx_bytesMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._consumerMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cpu_draft_target_stateMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cpu_fallback_request_eligibleMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cpu_isolated_binaryMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cpu_isolated_replayMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._ctx_integrity_flagsMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cuda_compute_capsMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._cuda_sm_gate_errorMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._detect_audio_type_strictMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._detokMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._diffusion_gpu_argMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._directoriesMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._download_companion_ggufMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._download_dflashMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._download_dsparkMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._download_ggufMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._download_mmprojMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._download_mtpMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._draft_backend_forMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._draft_kv_symmetryMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._drain_stdoutMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._drop_env_flash_attnMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._drop_env_quantized_v_cacheMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._dspark_release_is_brokenMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._dspark_wins_autoMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._dyld_reason_afterMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._dyld_tried_verdictMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._effective_gpu_countMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._emit_child_gpu_visibilityMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._emit_dflashMethodstudio/backend/core/inference/llama_cpp.py
LlamaCppBackend._emit_dsparkMethodstudio/backend/core/inference/llama_cpp.py
… +583 more
Signature changed
_admin_credentialFunctionstudio/backend/auth/authentication.py
runLintBatchFunctionstudio/backend/core/data_recipe/oxc-validator/validate.mjs
runValidationFunctionstudio/backend/core/data_recipe/oxc-validator/validate.mjs
ApiMonitor.__init__Methodstudio/backend/core/inference/api_monitor.py
fit_checkpoint_contextFunctionstudio/backend/core/inference/checkpoint.py
fit_rolling_contextFunctionstudio/backend/core/inference/context_window.py
_error_sse_lineFunctionstudio/backend/core/inference/external_provider.py
acquire_forFunctionstudio/backend/core/inference/gpu_arbiter.py
_note_endFunctionstudio/backend/core/inference/llama_keepwarm.py
_note_pendingFunctionstudio/backend/core/inference/llama_keepwarm.py
_note_startFunctionstudio/backend/core/inference/llama_keepwarm.py
_note_unpendingFunctionstudio/backend/core/inference/llama_keepwarm.py
_note_untracked_endFunctionstudio/backend/core/inference/llama_keepwarm.py
_unload_gateFunctionstudio/backend/core/inference/llama_keepwarm.py
_quota_metadataFunctionstudio/backend/core/inference/openai_codex_client.py
InferenceOrchestrator._wait_responseMethodstudio/backend/core/inference/orchestrator.py
ToolLoopController.prepare_callMethodstudio/backend/core/inference/tool_loop_controller.py
coerce_tool_argumentsFunctionstudio/backend/core/inference/tool_loop_controller.py
LlamaServerBackend._currentMethodstudio/backend/core/rag/embed_llama_server.py
LlamaServerBackend._ensure_readyMethodstudio/backend/core/rag/embed_llama_server.py
LlamaServerBackend._postMethodstudio/backend/core/rag/embed_llama_server.py
LlamaServerBackend._resolve_model_pathMethodstudio/backend/core/rag/embed_llama_server.py
LlamaServerBackend._restartMethodstudio/backend/core/rag/embed_llama_server.py
LlamaServerBackend._spawnMethodstudio/backend/core/rag/embed_llama_server.py
LlamaServerBackend._spawn_onceMethodstudio/backend/core/rag/embed_llama_server.py
_build_st_backend_or_fallbackFunctionstudio/backend/core/rag/embeddings.py
_get_backendFunctionstudio/backend/core/rag/embeddings.py
_switch_to_llama_fallbackFunctionstudio/backend/core/rag/embeddings.py
active_backend_is_llamaFunctionstudio/backend/core/rag/embeddings.py
search_for_autoinjectFunctionstudio/backend/core/rag/tool.py
_research_question_contextFunctionstudio/backend/core/research_runs.py
_cache_inventory_fieldsFunctionstudio/backend/hub/services/models/cache_inventory.py
_addFunctionstudio/backend/hub/utils/paths.py
save_thread_messageFunctionstudio/backend/routes/chat_history.py
_TrackedCancel.__init__Methodstudio/backend/routes/inference.py
_apply_compaction_nudgeFunctionstudio/backend/routes/inference.py
_checkpoint_needs_searchFunctionstudio/backend/routes/inference.py
_estimate_gguf_required_gbFunctionstudio/backend/routes/inference.py
_load_model_implFunctionstudio/backend/routes/inference.py
_maybe_auto_switch_modelFunctionstudio/backend/routes/inference.py
_openai_llama_admission_media_tokensFunctionstudio/backend/routes/inference.py
_openai_llama_admission_tokensFunctionstudio/backend/routes/inference.py
_stats_finish_reasonFunctionstudio/backend/routes/inference.py
get_kv_cache_estimateFunctionstudio/backend/routes/models.py
_llama_backend_activeFunctionstudio/backend/routes/settings.py
ActiveGeneration.__init__Methodstudio/backend/state/active_generations.py
_fingerprintFunctionstudio/backend/storage/profile_stats_db.py
compute_profile_statsFunctionstudio/backend/storage/profile_stats_db.py
create_and_bind_terminal_fallbackFunctionstudio/backend/storage/research_runs_db.py
set_planFunctionstudio/backend/storage/research_runs_db.py
clear_chat_historyFunctionstudio/backend/storage/studio_db.py
clear_chat_history_with_replay_statusFunctionstudio/backend/storage/studio_db.py
sync_chat_messagesFunctionstudio/backend/storage/studio_db.py
upsert_chat_messageFunctionstudio/backend/storage/studio_db.py
clear_with_idsFunctionstudio/backend/tests/test_chat_history_routes.py
seed_userFunctionstudio/backend/tests/test_keyless_api_access.py
TestApiMonitorProviderAndCompletionStreams.fake_sendMethodstudio/backend/tests/test_openai_tool_passthrough.py
_upstream_messageFunctionstudio/backend/tests/test_passthrough_healing.py
slow_computeFunctionstudio/backend/tests/test_profile_stats.py
fake_postFunctionstudio/backend/tests/test_rag_embed_llama_server.py
fake_spawnFunctionstudio/backend/tests/test_rag_embed_llama_server.py
fake_spawn_onceFunctionstudio/backend/tests/test_rag_embed_llama_server.py
_buildFunctionstudio/backend/tests/test_rag_embeddings.py
TestAGgufWithNoNativeContext.test_the_reduction_still_pins_without_a_native_contextMethodstudio/backend/tests/test_slot_reduction_context_refit.py
_planFunctionstudio/backend/tests/test_slot_refit_platform_matrix.py
set_rag_embedding_modelFunctionstudio/backend/utils/embedding_model_settings.py
useFenceReachedFunctionio/frontend/src/components/assistant-ui/code-fence-defer.tsx
createRepairParityFunctionend/src/components/assistant-ui/streaming-render-schedule.ts
findCommitBoundaryFunctionend/src/components/assistant-ui/streaming-render-schedule.ts
messageHasResearchRunIdFunctiontend/src/components/assistant-ui/thread-research-presence.ts
threadHasResearchMessageFunctiontend/src/components/assistant-ui/thread-research-presence.ts
ToolFallbackRootFunctiontudio/frontend/src/components/assistant-ui/tool-fallback.tsx
CodeExecutionToolUIImplFunctionntend/src/components/assistant-ui/tool-ui-code-execution.tsx
KnowledgeBaseToolUIImplFunctionntend/src/components/assistant-ui/tool-ui-knowledge-base.tsx
WebSearchToolUIImplFunction/frontend/src/components/assistant-ui/tool-ui-web-search.tsx
hasBigEndianGgufMarkerFunctionstudio/frontend/src/features/chat/api/chat-adapter.ts
isMcpImageToolResultFunctionstudio/frontend/src/features/chat/api/chat-adapter.ts
persistResolvedQueuedModelFunctionstudio/frontend/src/features/chat/api/chat-adapter.ts
resolveQueuedEmptyLocalModelFunctionstudio/frontend/src/features/chat/api/chat-adapter.ts
GenerationLengthError.constructorMethodstudio/frontend/src/features/chat/api/chat-api.ts
countChatInputTokensFunctionstudio/frontend/src/features/chat/api/chat-api.ts
estimateKvCacheFunctionstudio/frontend/src/features/chat/api/chat-api.ts
loadModelFunctionstudio/frontend/src/features/chat/api/chat-api.ts
notifyChatHistoryUpdatedFunctionstudio/frontend/src/features/chat/api/chat-api.ts
saveChatMessageFunctionstudio/frontend/src/features/chat/api/chat-api.ts
streamChatCompletionsFunctionstudio/frontend/src/features/chat/api/chat-api.ts
syncChatMessagesFunctionstudio/frontend/src/features/chat/api/chat-api.ts
codeToolCanRunFunctionstudio/frontend/src/features/chat/api/code-tool-placement.ts
chatModelSwitchMetaFunctionend/src/features/chat/components/chat-model-notice-switch.ts
ChatModelNoticeFunction/frontend/src/features/chat/components/chat-model-notice.tsx
syncInferenceStatusToStoreFunctiono/frontend/src/features/chat/hooks/use-chat-model-runtime.ts
syncModelCapabilitiesFunctiono/frontend/src/features/chat/hooks/use-chat-model-runtime.ts
NewPromptFormFunctiond/src/features/chat/prompt-storage/prompt-storage-dialog.tsx
NewPromptListFormFunctiond/src/features/chat/prompt-storage/prompt-storage-dialog.tsx
loadConversationMessagesFunctiond/src/features/chat/prompt-storage/prompt-storage-dialog.tsx
ensureThreadRecordFunctionstudio/frontend/src/features/chat/runtime-provider.tsx
syncStoredChatMessagesFunctiondio/frontend/src/features/chat/utils/chat-history-storage.ts
modeAllowsContinuationFunctionstudio/frontend/src/features/chat/utils/continuation.ts
syncExportedRepositoryToBackendFunctionio/frontend/src/features/chat/utils/delete-thread-message.ts
mergeQueuedModelCapabilitiesFunctionrontend/src/features/chat/utils/queued-model-capabilities.ts
… +32 more
Added new API surface in @v0.1.804-beta
torch_is_rocmFunctionstudio/backend/core/_torchao_stub.py
mapBudgetMsFunctionstudio/backend/core/data_recipe/oxc-validator/validate.mjs
ApiMonitor._notify_terminalMethodstudio/backend/core/inference/api_monitor.py
ApiMonitor._terminal_callback_lockedMethodstudio/backend/core/inference/api_monitor.py
ApiMonitor._terminal_notification_lockedMethodstudio/backend/core/inference/api_monitor.py
ApiMonitor.acquire_terminal_callbackMethodstudio/backend/core/inference/api_monitor.py
ApiMonitor.release_terminal_callbackMethodstudio/backend/core/inference/api_monitor.py
ApiMonitor.set_terminal_callbackMethodstudio/backend/core/inference/api_monitor.py
ChatGenerationSupervisorClassstudio/backend/core/inference/chat_generation_runs.py
ChatGenerationSupervisor.__init__Methodstudio/backend/core/inference/chat_generation_runs.py
ChatGenerationSupervisor._cleanup_registrationMethodstudio/backend/core/inference/chat_generation_runs.py
ChatGenerationSupervisor._ensure_reservationMethodstudio/backend/core/inference/chat_generation_runs.py
ChatGenerationSupervisor._produceMethodstudio/backend/core/inference/chat_generation_runs.py
ChatGenerationSupervisor._task_doneMethodstudio/backend/core/inference/chat_generation_runs.py
ChatGenerationSupervisor.cancelMethodstudio/backend/core/inference/chat_generation_runs.py
ChatGenerationSupervisor.startMethodstudio/backend/core/inference/chat_generation_runs.py
ChatGenerationSupervisor.stopMethodstudio/backend/core/inference/chat_generation_runs.py
_SSEDecoderClassstudio/backend/core/inference/chat_generation_runs.py
_SSEDecoder.__init__Methodstudio/backend/core/inference/chat_generation_runs.py
_SSEDecoder.feedMethodstudio/backend/core/inference/chat_generation_runs.py
_background_requestFunctionstudio/backend/core/inference/chat_generation_runs.py
_chunk_errorFunctionstudio/backend/core/inference/chat_generation_runs.py
_chunk_finish_reasonFunctionstudio/backend/core/inference/chat_generation_runs.py
_close_iteratorFunctionstudio/backend/core/inference/chat_generation_runs.py
receiveFunctionstudio/backend/core/inference/chat_generation_runs.py
describe_unservable_tool_callFunctionstudio/backend/core/inference/context_refusal.py
_blamed_roleFunctionstudio/backend/core/inference/context_window.py
_blamed_role_for_turnFunctionstudio/backend/core/inference/context_window.py
_compact_one_callFunctionstudio/backend/core/inference/context_window.py
_compacted_argumentsFunctionstudio/backend/core/inference/context_window.py
_completed_phrase_forFunctionstudio/backend/core/inference/context_window.py
_executed_call_sitesFunctionstudio/backend/core/inference/context_window.py
_largest_leafFunctionstudio/backend/core/inference/context_window.py
_last_index_with_callFunctionstudio/backend/core/inference/context_window.py
_reply_floorFunctionstudio/backend/core/inference/context_window.py
_reply_for_callFunctionstudio/backend/core/inference/context_window.py
_reply_proves_a_writeFunctionstudio/backend/core/inference/context_window.py
_reply_shows_executionFunctionstudio/backend/core/inference/context_window.py
_shrinkFunctionstudio/backend/core/inference/context_window.py
_total_leavesFunctionstudio/backend/core/inference/context_window.py
clamp_compaction_headroom_ratioFunctionstudio/backend/core/inference/context_window.py
compact_completed_tool_argumentsFunctionstudio/backend/core/inference/context_window.py
compact_executed_call_argumentsFunctionstudio/backend/core/inference/context_window.py
compact_refused_tool_argumentsFunctionstudio/backend/core/inference/context_window.py
turn_is_servableFunctionstudio/backend/core/inference/context_window.py
_read_model_indexFunctionstudio/backend/core/inference/diffusion_krea2.py
_crashed_child_verdictFunctionstudio/backend/core/inference/diffusion_transformer_quant.py
_select_probe_cardFunctionstudio/backend/core/inference/diffusion_transformer_quant.py
dense_transformer_unsupported_reasonFunctionstudio/backend/core/inference/diffusion_transformer_quant.py
_apply_ollama_reasoning_controlsFunctionstudio/backend/core/inference/external_provider.py
GpuOwnerBusyErrorClassstudio/backend/core/inference/gpu_arbiter.py
GpuOwnerBusyError.__init__Methodstudio/backend/core/inference/gpu_arbiter.py
InferenceActivityReservationClassstudio/backend/core/inference/llama_keepwarm.py
InferenceActivityReservation.__init__Methodstudio/backend/core/inference/llama_keepwarm.py
InferenceActivityReservation.finishMethodstudio/backend/core/inference/llama_keepwarm.py
InferenceActivityReservation.reserveMethodstudio/backend/core/inference/llama_keepwarm.py
InferenceActivityReservation.startMethodstudio/backend/core/inference/llama_keepwarm.py
_claim_non_preview_slotFunctionstudio/backend/core/inference/llama_keepwarm.py
_is_preview_pathFunctionstudio/backend/core/inference/llama_keepwarm.py
_note_admitted_endFunctionstudio/backend/core/inference/llama_keepwarm.py
_preview_swap_activeFunctionstudio/backend/core/inference/llama_keepwarm.py
_preview_swap_genFunctionstudio/backend/core/inference/llama_keepwarm.py
begin_preview_serializer_waitFunctionstudio/backend/core/inference/llama_keepwarm.py
cancel_preview_serializer_waitFunctionstudio/backend/core/inference/llama_keepwarm.py
mark_current_response_failedFunctionstudio/backend/core/inference/llama_keepwarm.py
mark_response_failedFunctionstudio/backend/core/inference/llama_keepwarm.py
note_admitted_inferenceFunctionstudio/backend/core/inference/llama_keepwarm.py
note_preview_swapFunctionstudio/backend/core/inference/llama_keepwarm.py
note_preview_swap_beginFunctionstudio/backend/core/inference/llama_keepwarm.py
note_preview_swap_endFunctionstudio/backend/core/inference/llama_keepwarm.py
other_admitted_inference_countFunctionstudio/backend/core/inference/llama_keepwarm.py
other_non_preview_pending_countFunctionstudio/backend/core/inference/llama_keepwarm.py
other_preview_inflight_countFunctionstudio/backend/core/inference/llama_keepwarm.py
preview_swapped_since_entryFunctionstudio/backend/core/inference/llama_keepwarm.py
resume_preview_after_serializerFunctionstudio/backend/core/inference/llama_keepwarm.py
set_current_response_scopeFunctionstudio/backend/core/inference/llama_keepwarm.py
_pageable_env_valueFunctionstudio/backend/core/inference/llama_server_args.py
_pageable_mode_replacementFunctionstudio/backend/core/inference/llama_server_args.py
extra_args_select_load_modeFunctionstudio/backend/core/inference/llama_server_args.py
fit_target_margin_inFunctionstudio/backend/core/inference/llama_server_args.py
force_pageable_loadFunctionstudio/backend/core/inference/llama_server_args.py
matches_explicit_ctx_overrideFunctionstudio/backend/core/inference/llama_server_args.py
memory_env_selects_load_modeFunctionstudio/backend/core/inference/llama_server_args.py
split_policy_starves_devicesFunctionstudio/backend/core/inference/llama_server_args.py
_block_imageFunctionstudio/backend/core/inference/mcp_client.py
_block_linkFunctionstudio/backend/core/inference/mcp_client.py
_block_textFunctionstudio/backend/core/inference/mcp_client.py
_image_mimeFunctionstudio/backend/core/inference/mcp_client.py
_resource_mimeFunctionstudio/backend/core/inference/mcp_client.py
_uri_mimeFunctionstudio/backend/core/inference/mcp_client.py
_EmptyBreakdownClassstudio/backend/core/inference/memory_contract.py
_EmptyBreakdown.__repr__Methodstudio/backend/core/inference/memory_contract.py
_UnsetClassstudio/backend/core/inference/memory_contract.py
_Unset.__bool__Methodstudio/backend/core/inference/memory_contract.py
build_memory_estimateFunctionstudio/backend/core/inference/memory_contract.py
project_estimate_memory_responseFunctionstudio/backend/core/inference/memory_contract.py
project_kv_cache_estimateFunctionstudio/backend/core/inference/memory_contract.py
AccessClassstudio/backend/core/inference/offload_cost_model.py
HostProfileClassstudio/backend/core/inference/offload_cost_model.py
HostProfile.generation_slowdownMethodstudio/backend/core/inference/offload_cost_model.py
… +3307 more