请通过执行“调试”->“Debug.Start Without Debugging”验证 web.config 中没有语法错误

本文详细介绍了在Window7环境下使用IIS7.0部署并运行ASP.NET程序时遇到错误的解决步骤。通过将应用程序池的托管管道模式从默认的Integrated更改为Classic,可以有效解决配置不兼容导致的调试问题。同时提供了确保服务器正确配置的方法及ASP.NET和ATLServer调试的相关指导。

window 7 运行asp.net程序出错-IIS7.0 检测到在集成的托管管道模式下不适用的ASP.NET设置的解决方法:

在应用程序池的高级设置里有个托管管道模式,默认值为Integrated,我们将其修改为Classic,就可以很好的解决问题了。


ASP.NET调试错误,现象如下:

---------------------------
Microsoft Visual Studio
---------------------------
无法在 Web 服务器上启动调试。请参见有关常见配置错误的帮助。在调试器外运行网页或许能提供进一步的信息。

确保服务器操作正确。请通过执行“调试”->“Debug.Start Without Debugging”验证 web.config 中没有语法错误。可能还需要参考联机文档中的 ASP.NET 和 ATL Server 调试主题。


---------------------------
确定   帮助   
---------------------------



<!-- -*- nxml-child-indent: 4; tab-width: 4; indent-tabs-mode: nil -*- --> <config> <!-- For more detailed documentation on typical configuration options please see: https://sdk.collaboraonline.com/docs/installation/Configuration.html --> <!-- Note: 'default' attributes are used to document a setting's default value as well as to use as fallback. --> <!-- Note: When adding a new entry, a default must be set in WSD in case the entry is missing upon deployment. --> <accessibility desc="Accessibility settings"> <enable type="bool" desc="Controls whether accessibility support should be enabled or not." default="false">false</enable> </accessibility> <allowed_languages desc="List of supported languages of Writing Aids (spell checker, grammar checker, thesaurus, hyphenation) on this instance. Allowing too many has negative effect on startup performance." default="de_DE en_GB en_US es_ES fr_FR it nl pt_BR pt_PT ru">de_DE en_GB en_US es_ES fr_FR it nl pt_BR pt_PT ru</allowed_languages> <!-- These are the settings of external (remote) spellchecker and grammar checker services. Currently LanguageTool and Duden Korrekturserver APIs are supported, you can set either of them. By default they are disabled. To turn the support on, please set "enabled" property to true. It works with self hosted or cloud services, free and premium as well. The "base_url" may be https://api.languagetoolplus.com/v2 if the cloud version of LanguageTool is used. Please note that your data in the document e.g. the text part of it will be sent to the cloud API. Please read the respective privacy policies, e.g. https://languagetool.org/legal/privacy. --> <languagetool desc="Remote API settings for spell and grammar checking"> <enabled desc="Enable Remote Spell and Grammar Checker" type="bool" default="false">false</enabled> <base_url desc="HTTP endpoint for the API server, without /check or /languages postfix at the end." type="string" default=""></base_url> <user_name desc="LanguageTool or Duden account username for premium usage." type="string" default=""></user_name> <api_key desc="API key provided by LanguageTool or Duden account for premium usage." type="string" default=""></api_key> <ssl_verification desc="Enable or disable SSL verification. You may have to disable it in test environments with self-signed certificates." type="string" default="true">true</ssl_verification> <rest_protocol desc="REST API protocol. For LanguageTool leave it blank, for Duden Korrekturserver use the string 'duden'." type="string" default=""></rest_protocol> </languagetool> <deepl desc="DeepL API settings for translation service"> <enabled desc="If true, shows translate option as a menu entry in the compact view and as an icon in the tabbed view." type="bool" default="false">false</enabled> <api_url desc="URL for the API" type="string" default=""></api_url> <auth_key desc="Auth Key generated by your account" type="string" default=""></auth_key> </deepl> <sys_template_path desc="Path to a template tree with shared libraries etc to be used as source for chroot jails for child processes." type="path" relative="true" default="systemplate"></sys_template_path> <child_root_path desc="Path to the directory under which the chroot jails for the child processes will be created. Should be on the same file system as systemplate and lotemplate. Must be an empty directory." type="path" relative="true" default="jails"></child_root_path> <mount_jail_tree desc="Controls whether the systemplate and lotemplate contents are mounted or not, which is much faster than the default of linking/copying each file." type="bool" default="true">true</mount_jail_tree> <server_name desc="External hostname:port of the server running coolwsd. If empty, it's derived from the request (please set it if this doesn't work). May be specified when behind a reverse-proxy or when the hostname is not reachable directly." type="string" default=""></server_name> <file_server_root_path desc="Path to the directory that should be considered root for the file server. This should be the directory containing cool." type="path" relative="true" default="browser/../"></file_server_root_path> <hexify_embedded_urls desc="Enable to protect encoded URLs from getting decoded by intermediate hops. Particularly useful on Azure deployments" type="bool" default="false">false</hexify_embedded_urls> <experimental_features desc="Enable/Disable experimental features" type="bool" default="true">true</experimental_features> <memproportion desc="The maximum percentage of available memory consumed by all of the Collabora Online Development Edition processes, after which we start cleaning up idle documents. If cgroup memory limits are set, this is the maximum percentage of that limit to consume." type="double" default="80.0"></memproportion> <num_prespawn_children desc="Number of child processes to keep started in advance and waiting for new clients." type="uint" default="4">4</num_prespawn_children> <fetch_update_check desc="Every number of hours will fetch latest version data. Defaults to 10 hours." type="uint" default="10">10</fetch_update_check> <allow_update_popup desc="Allows notification about an update in the editor" type="bool" default="true">true</allow_update_popup> <per_document desc="Document-specific settings, including LO Core settings."> <max_concurrency desc="The maximum number of threads to use while processing a document." type="uint" default="4">4</max_concurrency> <batch_priority desc="A (lower) priority for use by batch eg. convert-to processes to avoid starving interactive ones" type="uint" default="5">5</batch_priority> <bgsave_priority desc="A (lower) priority for use by background save processes to free time for interactive ones" type="uint" default="5">5</bgsave_priority> <bgsave_timeout_secs desc="The default maximum number of seconds to wait for the background save processes to finish before giving up and reverting to synchronous saving" type="uint" default="120">120</bgsave_timeout_secs> <redlining_as_comments desc="If true show red-lines as comments" type="bool" default="false">false</redlining_as_comments> <pdf_resolution_dpi desc="The resolution, in DPI, used to render PDF documents as image. Memory consumption grows proportionally. Must be a positive value less than 385. Defaults to 96." type="uint" default="96">96</pdf_resolution_dpi> <idle_timeout_secs desc="The maximum number of seconds before unloading an idle document. Defaults to 1 hour." type="uint" default="3600">3600</idle_timeout_secs> <idlesave_duration_secs desc="The number of idle seconds after which document, if modified, should be saved. Disabled when 0. Defaults to 30 seconds." type="uint" default="30">30</idlesave_duration_secs> <autosave_duration_secs desc="The number of seconds after which document, if modified, should be saved. Disabled when 0. Defaults to 5 minutes." type="uint" default="300">300</autosave_duration_secs> <background_autosave desc="Allow auto-saves to occur in a forked background process where possible." type="bool" default="true">true</background_autosave> <background_manualsave desc="Allow manual save to occur in a forked background process where possible" type="bool" default="true">true</background_manualsave> <always_save_on_exit desc="On exiting the last editor, always perform a save and upload if the document had been modified. This is to allow the storage to store the document, if it had skipped doing so, previously, as an optimization." type="bool" default="false">false</always_save_on_exit> <limit_virt_mem_mb desc="The maximum virtual memory allowed to each document process. 0 for unlimited." type="uint">0</limit_virt_mem_mb> <limit_stack_mem_kb desc="The maximum stack size allowed to each document process. 0 for unlimited." type="uint">8000</limit_stack_mem_kb> <limit_file_size_mb desc="The maximum file size allowed to each document process to write. 0 for unlimited." type="uint">0</limit_file_size_mb> <limit_num_open_files desc="The maximum number of files allowed to each document process to open. 0 for unlimited." type="uint">0</limit_num_open_files> <limit_load_secs desc="Maximum number of seconds to wait for a document load to succeed. 0 for unlimited." type="uint" default="100">100</limit_load_secs> <limit_store_failures desc="Maximum number of consecutive save-and-upload to storage failures when unloading the document. 0 for unlimited (not recommended)." type="uint" default="5">5</limit_store_failures> <limit_convert_secs desc="Maximum number of seconds to wait for a document conversion to succeed. 0 for unlimited." type="uint" default="100">100</limit_convert_secs> <min_time_between_saves_ms desc="Minimum number of milliseconds between saving the document on disk." type="uint" default="500">500</min_time_between_saves_ms> <min_time_between_uploads_ms desc="Minimum number of milliseconds between uploading the document to storage." type="uint" default="5000">5000</min_time_between_uploads_ms> <cleanup desc="Checks for resource consuming (bad) documents and kills associated kit process. A document is considered resource consuming (bad) if is in idle state for idle_time_secs period and memory usage passed limit_dirty_mem_mb or CPU usage passed limit_cpu_per" enable="true"> <cleanup_interval_ms desc="Interval between two checks" type="uint" default="10000">10000</cleanup_interval_ms> <bad_behavior_period_secs desc="Minimum time period for a document to be in bad state before associated kit process is killed. If in this period the condition for bad document is not met once then this period is reset" type="uint" default="60">60</bad_behavior_period_secs> <idle_time_secs desc="Minimum idle time for a document to be candidate for bad state" type="uint" default="300">300</idle_time_secs> <limit_dirty_mem_mb desc="Minimum memory usage for a document to be candidate for bad state" type="uint" default="3072">3072</limit_dirty_mem_mb> <limit_cpu_per desc="Minimum CPU usage for a document to be candidate for bad state" type="uint" default="85">85</limit_cpu_per> <lost_kit_grace_period_secs desc="The minimum grace period for a lost kit process (not referenced by coolwsd) to resolve its lost status before it is terminated. To disable the cleanup of lost kits use value 0" default="120">120</lost_kit_grace_period_secs> </cleanup> </per_document> <per_view desc="View-specific settings."> <out_of_focus_timeout_secs desc="The maximum number of seconds before dimming and stopping updates when the browser tab is no longer in focus. Defaults to 300 seconds." type="uint" default="300">300</out_of_focus_timeout_secs> <idle_timeout_secs desc="The maximum number of seconds before dimming and stopping updates when the user is no longer active (even if the browser is in focus). Defaults to 15 minutes." type="uint" default="900">900</idle_timeout_secs> <custom_os_info desc="Custom string shown as OS version in About dialog, get from system if empty." type="string" default=""></custom_os_info> <min_saved_message_timeout_secs type="uint" desc="The minimum number of seconds before the last modified message is being displayed." default="6">6</min_saved_message_timeout_secs> </per_view> <ver_suffix desc="Appended to etags to allow easy refresh of changed files during development" type="string" default=""></ver_suffix> <logging> <color type="bool">true</color> <!-- Note to developers: When you do "make run", the logging.level will be set on the coolwsd command line, so if you want to change it for your testing, do it in Makefile.am, not here. --> <level type="string" desc="Can be 0-8 (with the lowest numbers being the least verbose), or none (turns off logging), fatal, critical, error, warning, notice, information, debug, trace" default="warning">warning</level> <level_startup type="string" desc="As for level - but for the initial startup phase which is most problematic, logging reverts to level configured above when startup is complete" default="trace">trace</level_startup> <disabled_areas type="string" desc="High verbosity logging ie. info to trace are disable-able, comma separated: Generic, Pixel, Socket, WebSocket, Http, WebServer, Storage, WOPI, Admin, Javascript" default="Socket,WebSocket,Admin,Pixel">Socket,WebSocket,Admin,Pixel</disabled_areas> <most_verbose_level_settable_from_client type="string" desc="A loggingleveloverride message from the client can not set a more verbose log level than this" default="notice">notice</most_verbose_level_settable_from_client> <least_verbose_level_settable_from_client type="string" desc="A loggingleveloverride message from a client can not set a less verbose log level than this" default="fatal">fatal</least_verbose_level_settable_from_client> <protocol type="bool" desc="Enable minimal client-site JS protocol logging from the start">false</protocol> <!-- lokit_sal_log example: Log WebDAV-related messages, that is interesting for debugging Insert - Image operation: "+TIMESTAMP+INFO.ucb.ucp.webdav+WARN.ucb.ucp.webdav" See also: https://docs.libreoffice.org/sal/html/sal_log.html --> <lokit_sal_log type="string" desc="Fine tune log messages from LOKit. Default is to suppress log messages from LOKit." default="-INFO-WARN">-INFO-WARN</lokit_sal_log> <file enable="false"> <!-- If you use other path than /var/log and you run coolwsd from systemd, make sure that you enable that path in coolwsd.service (ReadWritePaths). Also the log file path must be writable by the 'cool' user. --> <property name="path" desc="Log file path.">/var/log/coolwsd.log</property> <property name="rotation" desc="Log file rotation strategy. See Poco FileChannel.">never</property> <property name="archive" desc="Append either timestamp or number to the archived log filename.">timestamp</property> <property name="compress" desc="Enable/disable log file compression.">true</property> <property name="purgeAge" desc="The maximum age of log files to preserve. See Poco FileChannel.">10 days</property> <property name="purgeCount" desc="The maximum number of log archives to preserve. Use 'none' to disable purging. See Poco FileChannel.">10</property> <property name="rotateOnOpen" desc="Enable/disable log file rotation on opening.">true</property> <property name="flush" desc="Enable/disable flushing after logging each line. May harm performance. Note that without flushing after each line, the log lines from the different processes will not appear in chronological order.">false</property> </file> <anonymize> <anonymize_user_data type="bool" desc="Enable to anonymize/obfuscate of user-data in logs. If default is true, it was forced at compile-time and cannot be disabled." default="false">false</anonymize_user_data> <anonymization_salt type="uint" desc="The salt used to anonymize/obfuscate user-data in logs. Use a secret 64-bit random number." default="82589933">82589933</anonymization_salt> </anonymize> <docstats type="bool" desc="Enable to see document handling information in logs." default="false">false</docstats> <userstats desc="Enable user stats. i.e: logs the details of a file and user" type="bool" default="false">false</userstats> <disable_server_audit type="bool" desc="Disabled server audit dialog and notification. Admin will no longer see warnings in the application user interface. This doesn't affect log file." default="false">false</disable_server_audit> </logging> <canvas_slideshow_enabled type="bool" desc="If true, WebGl presentation rendered on the client side is enabled, otherwise interactive SVG is used." default="true">true</canvas_slideshow_enabled> <logging_ui_cmd> <merge type="bool" desc="If true, repeated commands after each other will be merged into 1 line. If false, every command will be 1 new line." default="true">true</merge> <merge_display_end_time type="bool" desc="If true, the duration of the merged command will also be logged." default="false">true</merge_display_end_time> <file enable="false"> <!-- If you use other path than /var/log and you run coolwsd from systemd, make sure that you enable that path in coolwsd.service (ReadWritePaths). Also the log file path must be writable by the 'cool' user. --> <property name="path" desc="Log file path.">/var/log/coolwsd-ui-cmd.log</property> <property name="purgeCount" desc="The maximum number of log archives to preserve. Use 'none' to disable purging. See Poco FileChannel.">10</property> <property name="rotateOnOpen" desc="Enable/disable log file rotation on opening.">true</property> <property name="flush" desc="Enable/disable flushing after logging each line. May harm performance. Note that without flushing after each line, the log lines from the different processes will not appear in chronological order.">false</property> </file> </logging_ui_cmd> <!-- Note to developers: When you do "make run", the trace_event[@enable] will be set on the coolwsd command line, so if you want to change it for your testing, do it in Makefile.am, not here. --> <trace_event desc="The possibility to turn on generation of a Chrome Trace Event file" enable="false"> <path desc="Output path for the Trace Event file, to which they will be written if turned on at run-time" type="string" default="/var/log/coolwsd.trace.json">/var/log/coolwsd.trace.json</path> </trace_event> <browser_logging desc="Logging in the browser console" default="false">false</browser_logging> <trace desc="Dump commands and notifications for replay. When 'snapshot' is true, the source file is copied to the path first." enable="false"> <path desc="Output path to hold trace file and docs. Use '%' for timestamp to avoid overwriting. For example: /some/path/to/cooltrace-%.gz" compress="true" snapshot="false"></path> <filter> <message desc="Regex pattern of messages to exclude"></message> </filter> <outgoing> <record desc="Whether or not to record outgoing messages" default="false">false</record> </outgoing> </trace> <net desc="Network settings"> <!-- On systems where localhost resolves to IPv6 [::1] address first, when net.proto is all and net.listen is loopback, coolwsd unexpectedly listens on [::1] only. You need to change net.proto to IPv4, if you want to use 127.0.0.1. --> <proto type="string" default="all" desc="Protocol to use IPv4, IPv6 or all for both">all</proto> <listen type="string" default="any" desc="Listen address that coolwsd binds to. Can be 'any' or 'loopback'.">any</listen> <!-- this allows you to shift all of our URLs into a sub-path from https://my.com/browser/a123... to https://my.com/my/sub/path/browser/a123... --> <service_root type="path" default="" desc="Prefix the base URL for all the pages, websockets, etc. with this path. This includes the discovery URL."></service_root> <post_allow desc="Allow/deny client IP address for POST(REST)." allow="true"> <host desc="The IPv4 private 192.168 block as plain IPv4 dotted decimal addresses.">192\.168\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="Ditto, but as IPv4-mapped IPv6 addresses">::ffff:192\.168\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="The IPv4 loopback (localhost) address.">127\.0\.0\.1</host> <host desc="Ditto, but as IPv4-mapped IPv6 address">::ffff:127\.0\.0\.1</host> <host desc="The IPv6 loopback (localhost) address.">::1</host> <host desc="The IPv4 private 172.16.0.0/12 subnet part 1.">172\.1[6789]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="Ditto, but as IPv4-mapped IPv6 addresses">::ffff:172\.1[6789]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="The IPv4 private 172.16.0.0/12 subnet part 2.">172\.2[0-9]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="Ditto, but as IPv4-mapped IPv6 addresses">::ffff:172\.2[0-9]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="The IPv4 private 172.16.0.0/12 subnet part 3.">172\.3[01]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="Ditto, but as IPv4-mapped IPv6 addresses">::ffff:172\.3[01]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="The IPv4 private 10.0.0.0/8 subnet (Podman).">10\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="Ditto, but as IPv4-mapped IPv6 addresses">::ffff:10\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}</host> </post_allow> <lok_allow desc="Allowed hosts as an external data source inside edited files. All allowed post_allow.host and storage.wopi entries are also considered to be allowed as a data source. Used for example in: PostMessage Action_InsertGraphic, =WEBSERVICE() function, external reference in the cell."> <host desc="The IPv4 private 192.168 block as plain IPv4 dotted decimal addresses.">192\.168\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="Ditto, but as IPv4-mapped IPv6 addresses">::ffff:192\.168\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="The IPv4 loopback (localhost) address.">127\.0\.0\.1</host> <host desc="Ditto, but as IPv4-mapped IPv6 address">::ffff:127\.0\.0\.1</host> <host desc="The IPv6 loopback (localhost) address.">::1</host> <host desc="The IPv4 private 172.16.0.0/12 subnet part 1.">172\.1[6789]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="Ditto, but as IPv4-mapped IPv6 addresses">::ffff:172\.1[6789]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="The IPv4 private 172.16.0.0/12 subnet part 2.">172\.2[0-9]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="Ditto, but as IPv4-mapped IPv6 addresses">::ffff:172\.2[0-9]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="The IPv4 private 172.16.0.0/12 subnet part 3.">172\.3[01]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="Ditto, but as IPv4-mapped IPv6 addresses">::ffff:172\.3[01]\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="The IPv4 private 10.0.0.0/8 subnet (Podman).">10\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="Ditto, but as IPv4-mapped IPv6 addresses">::ffff:10\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}</host> <host desc="Localhost access by name">localhost</host> </lok_allow> <content_security_policy desc="Customize the CSP header by specifying one or more policy-directive, separated by semicolons. See w3.org/TR/CSP2"> </content_security_policy> <frame_ancestors> http://192.168.2.107:8881 http://10.1.200.64:* http://192.168.11.33:* </frame_ancestors> <connection_timeout_secs desc="Specifies the connection, send, recv timeout in seconds for connections initiated by coolwsd (such as WOPI connections)." type="int" default="30">30</connection_timeout_secs> <!-- this setting radically changes how online works, it should not be used in a production environment --> <proxy_prefix type="bool" default="false" desc="Enable a ProxyPrefix to be passed-in through which to redirect requests">false</proxy_prefix> </net> <ssl desc="SSL settings"> <!-- switches from https:// + wss:// to http:// + ws:// --> <enable type="bool" desc="Controls whether SSL encryption between coolwsd and the network is enabled (do not disable for production deployment). If default is false, must first be compiled with SSL support to enable." default="true">true</enable> <!-- SSL off-load can be done in a proxy, if so disable SSL, and enable termination below in production --> <termination desc="Connection via proxy where coolwsd acts as working via https, but actually uses http." type="bool" default="false">false</termination> <cert_file_path desc="Path to the cert file" type="path" relative="false">/etc/coolwsd/cert.pem</cert_file_path> <key_file_path desc="Path to the key file" type="path" relative="false">/etc/coolwsd/key.pem</key_file_path> <ca_file_path desc="Path to the ca file" type="path" relative="false">/etc/coolwsd/ca-chain.cert.pem</ca_file_path> <ssl_verification desc="Enable or disable SSL verification of hosts remote to coolwsd. If true SSL verification will be strict, otherwise certs of hosts will not be verified. You may have to disable it in test environments with self-signed certificates." type="string" default="false">false</ssl_verification> <cipher_list desc="List of OpenSSL ciphers to accept" type="string" default="ALL:!ADH:!LOW:!EXP:!MD5:@STRENGTH"></cipher_list> <hpkp desc="Enable HTTP Public key pinning" enable="false" report_only="false"> <max_age desc="HPKP's max-age directive - time in seconds browser should remember the pins" enable="true" type="uint" default="1000">1000</max_age> <report_uri desc="HPKP's report-uri directive - pin validation failure are reported at this URL" enable="false" type="string"></report_uri> <pins desc="Base64 encoded SPKI fingerprints of keys to be pinned"> <pin></pin> </pins> </hpkp> <sts desc="Strict-Transport-Security settings, per rfc6797. Subdomains are always included."> <enabled desc="Whether or not Strict-Transport-Security is enabled. Enable only when ready for production. Cannot be disabled without resetting the browsers." type="bool" default="false">false</enabled> <max_age desc="Strict-Transport-Security max-age directive, in seconds. 0 is allowed; please see rfc6797 for details. Defaults to 1 year." type="int" default="31536000">31536000</max_age> </sts> </ssl> <security desc="Altering these defaults potentially opens you to significant risk"> <seccomp desc="Should failure to enable seccomp system call filtering be a fatal error." type="bool" default="true">true</seccomp> <!-- deprecated: If capabilities is 'false', coolwsd will assume mount_namespaces of 'true' to achieve this goal, only avoiding chroot for process isolation if linux namespaces are unavailable --> <capabilities desc="Should we require capabilities to isolate processes into chroot jails" type="bool" default="true">true</capabilities> <jwt_expiry_secs desc="Time in seconds before the Admin Console's JWT token expires" type="int" default="1800">1800</jwt_expiry_secs> <enable_macros_execution desc="Specifies whether the macro execution is enabled in general. This will enable Basic and Python scripts to execute both installed and from documents. If it is set to false, the macro_security_level is ignored. If it is set to true, the mentioned entry specified the level of macro security." type="bool" default="false">false</enable_macros_execution> <macro_security_level desc="Level of Macro security. 1 (Medium) Confirmation required before executing macros from untrusted sources. 0 (Low, not recommended) All macros will be executed without confirmation." type="int" default="1">1</macro_security_level> <enable_websocket_urp desc="Should we enable URP (UNO remote protocol) communication over the websocket. This allows full control of the Kit child server to anyone with access to the websocket including executing macros without confirmation or running arbitrary shell commands in the jail." type="bool" default="false">false</enable_websocket_urp> <enable_metrics_unauthenticated desc="When enabled, the /cool/getMetrics endpoint will not require authentication." type="bool" default="false">false</enable_metrics_unauthenticated> <server_signature desc="Whether to send server signature in HTTP response headers" type="bool" default="false">false</server_signature> </security> <certificates> <database_path type="string" desc="Path to the NSS certificates that are available to all users" default=""></database_path> </certificates> <watermark> <opacity desc="Opacity of on-screen watermark from 0.0 to 1.0" type="double" default="0.2">0.2</opacity> <text desc="Watermark text to be displayed on the document if entered" type="string"></text> </watermark> <user_interface> <mode type="string" desc="Controls the user interface style. The 'default' means: Take the value from ui_defaults, or decide for one of compact or tabbed (default|compact|tabbed)" default="default">default</mode> <use_integration_theme desc="Use theme from the integrator" type="bool" default="true">true</use_integration_theme> <statusbar_save_indicator desc="Show saving status indicator in the statusbar" type="bool" default="true">true</statusbar_save_indicator> </user_interface> <storage desc="Backend storage"> <filesystem allow="false" /> <wopi desc="Allow/deny wopi storage." allow="true"> <max_file_size desc="Maximum document size in bytes to load. 0 for unlimited." type="uint">0</max_file_size> <locking desc="Locking settings"> <refresh desc="How frequently we should re-acquire a lock with the storage server, in seconds (default 15 mins) or 0 for no refresh" type="int" default="900">900</refresh> </locking> <alias_groups desc="default mode is 'first' it allows only the first host when groups are not defined. set mode to 'groups' and define group to allow multiple host and its aliases" mode="groups"> <group>192.168.2.107:8880,localhost:3000,10.1.200.64</group> </alias_groups> <is_legacy_server desc="Set to true for legacy server that need deprecated headers." type="bool" default="false">false</is_legacy_server> </wopi> <ssl desc="SSL settings"> <as_scheme type="bool" default="true" desc="When set we exclusively use the WOPI URI's scheme to enable SSL for storage">true</as_scheme> <enable type="bool" desc="If as_scheme is false or not set, this can be set to force SSL encryption between storage and coolwsd. When empty this defaults to following the ssl.enable setting"></enable> <cert_file_path desc="Path to the cert file. When empty this defaults to following the ssl.cert_file_path setting" type="path" relative="false"></cert_file_path> <key_file_path desc="Path to the key file. When empty this defaults to following the ssl.key_file_path setting" type="path" relative="false"></key_file_path> <ca_file_path desc="Path to the ca file. When empty this defaults to following the ssl.ca_file_path setting" type="path" relative="false"></ca_file_path> <cipher_list desc="List of OpenSSL ciphers to accept. If empty the defaults are used. These can be overridden only if absolutely needed."></cipher_list> </ssl> </storage> <admin_console desc="Web admin console settings."> <enable desc="Enable the admin console functionality" type="bool" default="true">true</enable> <enable_pam desc="Enable admin user authentication with PAM" type="bool" default="false">false</enable_pam> <username desc="The username of the admin console. Ignored if PAM is enabled."></username> <password desc="The password of the admin console. Deprecated on most platforms. Instead, use PAM or coolconfig to set up a secure password."></password> <logging desc="Log admin activities irrespective of logging.level"> <admin_login desc="log when an admin logged into the console" type="bool" default="true">true</admin_login> <metrics_fetch desc="log when metrics endpoint is accessed and metrics endpoint authentication is enabled" type="bool" default="true">true</metrics_fetch> <monitor_connect desc="log when external monitor gets connected" type="bool" default="true">true</monitor_connect> <admin_action desc="log when admin does some action for example killing a process" type="bool" default="true">true</admin_action> </logging> </admin_console> <monitors desc="Addresses of servers we connect to on start for monitoring"> <!-- <monitor desc="Address of the monitor and interval after which it should try reconnecting after disconnect" retryInterval="20">wss://foobar:234/ws</monitor> --> </monitors> <quarantine_files desc="Files are stored here to be examined later in cases of crashes or similar situation." default="false" enable="false"> <limit_dir_size_mb desc="Maximum directory size, in MBs. On exceeding the specified limit, older files will be deleted." default="250" type="uint">250</limit_dir_size_mb> <max_versions_to_maintain desc="How many versions of the same file to keep." default="5" type="uint">5</max_versions_to_maintain> <path desc="Absolute path of the directory under which quarantined files will be stored. Do not use a relative path." type="path" relative="false"></path> <expiry_min desc="Time in mins after quarantined files will be deleted." type="int" default="3000">3000</expiry_min> </quarantine_files> <cache_files desc="Files are cached here to speed up config support."> <path desc="Absolute path of the directory under which cached files will be stored. Do not use a relative path." type="path" relative="false"></path> <expiry_min desc="Time in mins after disuse at which cache files will be deleted." type="int" default="3000">1000</expiry_min> </cache_files> <extra_export_formats desc="Enable various extra export formats for additional compatibility. Note that disabling options here *only* disables them visually: these are all 'safe' to export, it might just be undesirable to show them, so you can't disable exporting these server-side"> <impress_swf desc="Enable exporting Adobe flash .swf files from presentations" type="bool" default="false">false</impress_swf> <impress_bmp desc="Enable exporting .bmp bitmap files from presentation slides" type="bool" default="false">false</impress_bmp> <impress_gif desc="Enable exporting .gif image files from presentation slides" type="bool" default="false">false</impress_gif> <impress_png desc="Enable exporting .png image files from presentation slides" type="bool" default="false">false</impress_png> <impress_svg desc="Enable exporting interactive .svg image files from presentations" type="bool" default="false">false</impress_svg> <impress_tiff desc="Enable exporting .tiff image files from presentation slides" type="bool" default="false">false</impress_tiff> </extra_export_formats> <serverside_config> <idle_timeout_secs desc="The maximum number of seconds before unloading an idle sub forkit. Defaults to 1 hour." type="uint" default="3600">3600</idle_timeout_secs> </serverside_config> <remote_config> <remote_url desc="remote server to which you will send request to get remote config in response" type="string" default=""></remote_url> </remote_config> <stop_on_config_change desc="Stop coolwsd whenever config files change." type="bool" default="false">false</stop_on_config_change> <remote_font_config> <url desc="URL of optional JSON file that lists fonts to be included in Online" type="string" default=""></url> </remote_font_config> <fonts_missing> <handling desc="How to handle fonts missing in a document: 'report', 'log', 'both', or 'ignore'" type="string" default="log">log</handling> </fonts_missing> <indirection_endpoint> <url desc="URL endpoint to server which servers routeToken in json format" type="string" default=""></url> <migration_timeout_secs desc="The maximum number of seconds waiting for shutdown migration message from indirection server before unloading an document. Defaults to 180 second." type="uint" default="180">180</migration_timeout_secs> <geolocation_setup> <enable desc="Enable geolocation_setup when using indirection server with geolocation configuration" type="bool" default="false">false</enable> <timezone desc="IANA timezone of server. For example: Europe/Berlin" type="string"></timezone> <allowed_websocket_origins desc="Origin header to get accepted during websocket upgrade"> <!-- <origin></origin> --> </allowed_websocket_origins> </geolocation_setup> <server_name desc="server name to show in cluster overview admin panel" type="string" default=""></server_name> </indirection_endpoint> <home_mode> <enable desc="Home users can enable this setting, which in turn disables welcome screen and user feedback popups, but also limits concurrent open connections to 20 and concurrent open documents to 10. The default means that number of concurrent open connections and concurrent open documents are unlimited, but welcome screen and user feedback cannot be switched off." type="bool" default="false">false</enable> </home_mode> <zotero desc="Zotero plugin configuration. For more details about Zotero visit https://www.zotero.org/"> <enable desc="Enable Zotero plugin." type="bool" default="true">true</enable> </zotero> <help_url desc="The Help root URL, or empty for no help (hides the Help buttons)" type="string" default="https://help.collaboraoffice.com/help.html?">https://help.collaboraoffice.com/help.html?</help_url> <overwrite_mode> <enable desc="Enable overwrite mode (user can use insert key)" type="bool" default="false">false</enable> </overwrite_mode> <wasm desc="WASM-specific settings"> <enable desc="Enable WASM support" type="bool" default="false">false</enable> <force desc="When enabled, all requests are redirected to WASM." type="bool" default="false">false</force> </wasm> <document_signing desc="Document signing settings"> <enable desc="Enable document signing" type="bool" default="true">true</enable> </document_signing> </config> 这是我的coolwsd.xml 这样可以吗
11-07
(venv) D:\Audio2Face\Audio2Face-3D-SDK>trtexec --version &&&& RUNNING TensorRT.trtexec [TensorRT v101401] [b48] # trtexec --version [11/27/2025-14:33:27] [I] TF32 is enabled by default. Add --noTF32 flag to further improve accuracy with some performance cost. === Model Options === --onnx=<file> ONNX model === Build Options === --minShapes=spec Build with dynamic shapes using a profile with the min shapes provided --optShapes=spec Build with dynamic shapes using a profile with the opt shapes provided --maxShapes=spec Build with dynamic shapes using a profile with the max shapes provided --minShapesCalib=spec Calibrate with dynamic shapes using a profile with the min shapes provided --optShapesCalib=spec Calibrate with dynamic shapes using a profile with the opt shapes provided --maxShapesCalib=spec Calibrate with dynamic shapes using a profile with the max shapes provided Note: All three of min, opt and max shapes must be supplied. However, if only opt shapes is supplied then it will be expanded so that min shapes and max shapes are set to the same values as opt shapes. Input names can be wrapped with escaped single quotes (ex: 'Input:0'). Example input shapes spec: input0:1x3x256x256,input1:1x3x128x128 For scalars (0-D shapes), use input0:scalar or simply input0: with nothing after the colon. Each input shape is supplied as a key-value pair where key is the input name and value is the dimensions (including the batch dimension) to be used for that input. Each key-value pair has the key and value separated using a colon (:). Multiple input shapes can be provided via comma-separated key-value pairs, and each input name can contain at most one wildcard ('*') character. --inputIOFormats=spec Type and format of each of the input tensors (default = all inputs in fp32:chw) See --outputIOFormats help for the grammar of type and format list. Note: If this option is specified, please set comma-separated types and formats for all inputs following the same order as network inputs ID (even if only one input needs specifying IO format) or set the type and format once for broadcasting. --outputIOFormats=spec Type and format of each of the output tensors (default = all outputs in fp32:chw) Note: If this option is specified, please set comma-separated types and formats for all outputs following the same order as network outputs ID (even if only one output needs specifying IO format) or set the type and format once for broadcasting. IO Formats: spec ::= IOfmt[","spec] IOfmt ::= type:fmt type ::= "fp32"|"fp16"|"bf16"|"int32"|"int64"|"int8"|"uint8"|"bool" fmt ::= ("chw"|"chw2"|"hwc8"|"chw4"|"chw16"|"chw32"|"dhwc8"| "cdhw32"|"hwc"|"dla_linear"|"dla_hwc4"|"hwc16"|"dhwc")["+"fmt] --memPoolSize=poolspec Specify the size constraints of the designated memory pool(s) Supports the following base-2 suffixes: B (Bytes), G (Gibibytes), K (Kibibytes), M (Mebibytes). If none of suffixes is appended, the defualt unit is in MiB. Note: Also accepts decimal sizes, e.g. 0.25M. Will be rounded down to the nearest integer bytes. In particular, for dlaSRAM the bytes will be rounded down to the nearest power of 2. Pool constraint: poolspec ::= poolfmt[","poolspec] poolfmt ::= pool:size pool ::= "workspace"|"dlaSRAM"|"dlaLocalDRAM"|"dlaGlobalDRAM"|"tacticSharedMem" --profilingVerbosity=mode Specify profiling verbosity. mode ::= layer_names_only|detailed|none (default = layer_names_only). Please only assign once. --avgTiming=M Set the number of times averaged in each iteration for kernel selection (default = 8) --refit Mark the engine as refittable. This will allow the inspection of refittable layers and weights within the engine. --stripWeights Strip weights from plan. This flag works with either refit or refit with identical weights. Default to latter, but you can switch to the former by enabling both --stripWeights and --refit at the same time. --stripAllWeights Alias for combining the --refit and --stripWeights options. It marks all weights as refittable, disregarding any performance impact. Additionally, it strips all refittable weights after the engine is built. --weightless [Deprecated] this knob has been deprecated. Please use --stripWeights --versionCompatible, --vc Mark the engine as version compatible. This allows the engine to be used with newer versions of TensorRT on the same host OS, as well as TensorRT's dispatch and lean runtimes. --pluginInstanceNorm, --pi Set `kNATIVE_INSTANCENORM` to false in the ONNX parser. This will cause the ONNX parser to use a plugin InstanceNorm implementation over the native implementation when parsing. --uint8AsymmetricQuantizationDLA Set `kENABLE_UINT8_AND_ASYMMETRIC_QUANTIZATION_DLA` to true in the ONNX parser. This directs the onnx parser to allow UINT8 as a quantization data type and import zero point values directly without converting to float type or all-zero values. Should only be set with DLA software version >= 3.16. --useRuntime=runtime TensorRT runtime to execute engine. "lean" and "dispatch" require loading VC engine and do not support building an engine. runtime::= "full"|"lean"|"dispatch" --leanDLLPath=<file> External lean runtime DLL to use in version compatible mode. --excludeLeanRuntime When --versionCompatible is enabled, this flag indicates that the generated engine should not include an embedded lean runtime. If this is set, the user must explicitly specify a valid lean runtime to use when loading the engine. --monitorMemory Enable memory monitor report for debugging usage. (default = disabled) --sparsity=spec Control sparsity (default = disabled). Sparsity: spec ::= "disable", "enable", "force" Note: Description about each of these options is as below disable = do not enable sparse tactics in the builder (this is the default) enable = enable sparse tactics in the builder (but these tactics will only be considered if the weights have the right sparsity pattern) force = enable sparse tactics in the builder and force-overwrite the weights to have a sparsity pattern (even if you loaded a model yourself) [Deprecated] this knob has been deprecated. Please use <polygraphy surgeon prune> to rewrite the weights. --noTF32 Disable tf32 precision (default is to enable tf32, in addition to fp32) --fp16 Enable fp16 precision, in addition to fp32 (default = disabled) --bf16 Enable bf16 precision, in addition to fp32 (default = disabled) --int8 Enable int8 precision, in addition to fp32 (default = disabled) --fp8 Enable fp8 precision, in addition to fp32 (default = disabled) --int4 Enable int4 precision, in addition to fp32 (default = disabled) --best Enable all precisions to achieve the best performance (default = disabled) Note: --fp16, --bf16, --int8, --fp8, --int4, --best are deprecated and superseded by strong typing. The AutoCast tool (https://nvidia.github.io/TensorRT-Model-Optimizer/guides/8_autocast.html) can be used to convert the network to be strongly typed. --stronglyTyped Create a strongly typed network. (default = disabled) --directIO [Deprecated] Avoid reformatting at network boundaries. (default = disabled) --precisionConstraints=spec Control precision constraint setting. (default = none) Precision Constraints: spec ::= "none" | "obey" | "prefer" none = no constraints prefer = meet precision constraints set by --layerPrecisions/--layerOutputTypes if possible obey = meet precision constraints set by --layerPrecisions/--layerOutputTypes or fail otherwise --layerPrecisions=spec Control per-layer precision constraints. Effective only when precisionConstraints is set to "obey" or "prefer". (default = none) The specs are read left-to-right, and later ones override earlier ones. Each layer name can contain at most one wildcard ('*') character. Per-layer precision spec ::= layerPrecision[","spec] layerPrecision ::= layerName":"precision precision ::= "fp32"|"fp16"|"bf16"|"int32"|"int8" --layerOutputTypes=spec Control per-layer output type constraints. Effective only when precisionConstraints is set to "obey" or "prefer". (default = none The specs are read left-to-right, and later ones override earlier ones. Each layer name can contain at most one wildcard ('*') character. If a layer has more than one output, then multiple types separated by "+" can be provided for this layer. Per-layer output type spec ::= layerOutputTypes[","spec] layerOutputTypes ::= layerName":"type type ::= "fp32"|"fp16"|"bf16"|"int32"|"int8"["+"type] --layerDeviceTypes=spec Specify layer-specific device type. The specs are read left-to-right, and later ones override earlier ones. If a layer does not have a device type specified, the layer will opt for the default device type. Per-layer device type spec ::= layerDeviceTypePair[","spec] layerDeviceTypePair ::= layerName":"deviceType deviceType ::= "GPU"|"DLA" --decomposableAttentions=spec Specify decomposable attentions by comma-separated names. The specs are read left-to-right, and later ones override earlier ones. Each layer name can contain at most one wildcard ('*') character. --calib=<file> Read INT8 calibration cache file --safe Enable build safety certified engine, --stronglyTyped will be enabled by default with this option. If DLA is enabled, --buildDLAStandalone will be specified --dumpKernelText Dump the kernel text to a file, only available when --safe is enabled --buildDLAStandalone Enable build DLA standalone loadable which can be loaded by cuDLA, when this option is enabled, --allowGPUFallback is disallowed and --skipInference is enabled by default. Additionally, specifying --inputIOFormats and --outputIOFormats restricts I/O data type and memory layout (default = disabled) --allowGPUFallback When DLA is enabled, allow GPU fallback for unsupported layers (default = disabled) --consistency Perform consistency checking on safety certified engine --restricted Enable safety scope checking with kSAFETY_SCOPE build flag --saveEngine=<file> Save the serialized engine --loadEngine=<file> Load a serialized engine --asyncFileReader Load a serialized engine using async stream reader. Should be combined with --loadEngine. --getPlanVersionOnly Print TensorRT version when loaded plan was created. Works without deserialization of the plan. Use together with --loadEngine. Supported only for engines created with 8.6 and forward. --tacticSources=tactics Specify the tactics to be used by adding (+) or removing (-) tactics from the default tactic sources (default = all available tactics). Note: Currently only cuDNN, cuBLAS, cuBLAS-LT, and edge mask convolutions are listed as optional tactics. Tactic Sources: tactics ::= tactic[","tactics] tactic ::= (+|-)lib lib ::= "CUBLAS"|"CUBLAS_LT"|"CUDNN"|"EDGE_MASK_CONVOLUTIONS" |"JIT_CONVOLUTIONS" For example, to disable cudnn and enable cublas: --tacticSources=-CUDNN,+CUBLAS --noBuilderCache Disable timing cache in builder (default is to enable timing cache) --noCompilationCache Disable Compilation cache in builder, and the cache is part of timing cache (default is to enable compilation cache) --errorOnTimingCacheMiss Emit error when a tactic being timed is not present in the timing cache (default = false) --timingCacheFile=<file> Save/load the serialized global timing cache --preview=features Specify preview feature to be used by adding (+) or removing (-) preview features from the default Preview Features: features ::= feature[","features] feature ::= (+|-)flag flag ::= "aliasedPluginIO1003" |"runtimeActivationResize" |"profileSharing0806" --builderOptimizationLevel Set the builder optimization level. (default is 3) A Higher level allows TensorRT to spend more time searching for better optimization strategy. Valid values include integers from 0 to the maximum optimization level, which is currently 5. --maxTactics Set the maximum number of tactics to time when there is a choice of tactics. (default is -1) Larger number of tactics allow TensorRT to spend more building time on evaluating tactics. Default value -1 means TensorRT can decide the number of tactics based on its own heuristic. --hardwareCompatibilityLevel=mode Make the engine file compatible with other GPU architectures. (default = none) Hardware Compatibility Level: mode ::= "none" | "ampere+" | "sameComputeCapability" none = no compatibility ampere+ = compatible with Ampere and newer GPUs sameComputeCapability = compatible with GPUs that have the same Compute Capability version --runtimePlatform=platform Set the target platform for runtime execution. (default = SameAsBuild) When this option is enabled, --skipInference is enabled by default. RuntimePlatfrom: platform ::= "SameAsBuild" | "WindowsAMD64" SameAsBuild = no requirement for cross-platform compatibility. WindowsAMD64 = set the target platform for engine execution as Windows AMD64 system --tempdir=<dir> Overrides the default temporary directory TensorRT will use when creating temporary files. See IRuntime::setTemporaryDirectory API documentation for more information. --tempfileControls=controls Controls what TensorRT is allowed to use when creating temporary executable files. Should be a comma-separated list with entries in the format (in_memory|temporary):(allow|deny). in_memory: Controls whether TensorRT is allowed to create temporary in-memory executable files. temporary: Controls whether TensorRT is allowed to create temporary executable files in the filesystem (in the directory given by --tempdir). For example, to allow in-memory files and disallow temporary files: --tempfileControls=in_memory:allow,temporary:deny If a flag is unspecified, the default behavior is "allow". --maxAuxStreams=N Set maximum number of auxiliary streams per inference stream that TRT is allowed to use to run kernels in parallel if the network contains ops that can run in parallel, with the cost of more memory usage. Set this to 0 for optimal memory usage. (default = using heuristics) --profile Build with dynamic shapes using a profile with the min/max/opt shapes provided. Can be specified multiple times to create multiple profiles with contiguous index. (ex: --profile=0 --minShapes=<spec> --optShapes=<spec> --maxShapes=<spec> --profile=1 ...) --calibProfile Select the optimization profile to calibrate by index. (default = 0) --allowWeightStreaming Enable a weight streaming engine. Must be specified with --stronglyTyped. TensorRT will disable weight streaming at runtime unless --weightStreamingBudget is specified. --markDebug Specify list of names of tensors to be marked as debug tensors. Separate names with a comma --markUnfusedTensorsAsDebugTensors Mark unfused tensors as debug tensors --tilingOptimizationLevel Set the tiling optimization level. (default is 0) A Higher level allows TensorRT to spend more time searching for better optimization strategy. Valid values include integers from 0 to the maximum tiling optimization level(3). --l2LimitForTiling Set the L2 cache usage limit for tiling optimization(default is -1) --remoteAutoTuningConfig Set the remote auto tuning config. Must be specified with --safe. Format: protocol://username[:password]@hostname[:port]?param1=value1&param2=value2 Example: ssh://user:pass@192.0.2.100:22?remote_exec_path=/opt/tensorrt/bin&remote_lib_path=/opt/tensorrt/lib --refitFromOnnx Refit the loaded engine with the weights from the provided ONNX model. The model should be identical to the one used to generate the engine. === Inference Options === --shapes=spec Set input shapes for dynamic shapes inference inputs. Note: Input names can be wrapped with escaped single quotes (ex: 'Input:0'). Example input shapes spec: input0:1x3x256x256, input1:1x3x128x128 For scalars (0-D shapes), use input0:scalar or simply input0: with nothing after the colon. Each input shape is supplied as a key-value pair where key is the input name and value is the dimensions (including the batch dimension) to be used for that input. Each key-value pair has the key and value separated using a colon (:). Multiple input shapes can be provided via comma-separated key-value pairs, and each input name can contain at most one wildcard ('*') character. --loadInputs=spec Load input values from files (default = generate random inputs). Input names can be wrapped with single quotes (ex: 'Input:0') Input values spec ::= Ival[","spec] Ival ::= name":"file Consult the README for more information on generating files for custom inputs. --iterations=N Run at least N inference iterations (default = 10) --warmUp=N Run for N milliseconds to warmup before measuring performance (default = 200) --duration=N Run performance measurements for at least N seconds wallclock time (default = 3) If -1 is specified, inference will keep running unless stopped manually --sleepTime=N Delay inference start with a gap of N milliseconds between launch and compute (default = 0) --idleTime=N Sleep N milliseconds between two continuous iterations(default = 0) --infStreams=N Instantiate N execution contexts to run inference concurrently (default = 1) --exposeDMA Serialize DMA transfers to and from device (default = disabled). --noDataTransfers Disable DMA transfers to and from device (default = enabled). Note some device-to-host data transfers will remain if output dumping is enabled via the --dumpOutput or --exportOutput flags. --useManagedMemory Use managed memory instead of separate host and device allocations (default = disabled). --useSpinWait Actively synchronize on GPU events. This option may decrease synchronization time but increase CPU usage and power (default = disabled) --threads Enable multithreading to drive engines with independent threads or speed up refitting (default = disabled) --useCudaGraph Use CUDA graph to capture engine execution and then launch inference (default = disabled). This flag may be ignored if the graph capture fails. --timeDeserialize Time the amount of time it takes to deserialize the network and exit. --timeRefit Time the amount of time it takes to refit the engine before inference. --separateProfileRun Do not attach the profiler in the benchmark run; if profiling is enabled, a second profile run will be executed (default = disabled) --skipInference Exit after the engine has been built and skip inference perf measurement (default = disabled) --persistentCacheRatio Set the persistentCacheLimit in ratio, 0.5 represent half of max persistent L2 size (default = 0) --useProfile Set the optimization profile for the inference context (default = 0 ). --allocationStrategy=spec Specify how the internal device memory for inference is allocated. Strategy: spec ::= "static"|"profile"|"runtime" static = Allocate device memory based on max size across all profiles. profile = Allocate device memory based on max size of the current profile. runtime = Allocate device memory based on the actual input shapes. --saveDebugTensors Specify list of names of tensors to turn on the debug state and filename to save raw outputs to. These tensors must be specified as debug tensors during build time. Input values spec ::= Ival[","spec] Ival ::= name":"file --saveAllDebugTensors Save all debug tensors to files. Including debug tensors marked by --markDebug and --markUnfusedTensorsAsDebugTensors Multiple file formats can be saved simultaneously. Input values spec ::= format[","format] format ::= "summary"|"numpy"|"string"|"raw" --weightStreamingBudget Set the maximum amount of GPU memory TensorRT is allowed to use for weights. It can take on the following values: -2: (default) Disable weight streaming at runtime. -1: TensorRT will automatically decide the budget. 0-100%: Percentage of streamable weights that reside on the GPU. 0% saves the most memory but will have the worst performance. Requires the '%' character. >=0B: The exact amount of streamable weights that reside on the GPU. Supports the following base-2 suffixes: B (Bytes), G (Gibibytes), K (Kibibytes), M (Mebibytes). === Reporting Options === --verbose Use verbose logging (default = false) --avgRuns=N Report performance measurements averaged over N consecutive iterations (default = 10) --percentile=P1,P2,P3,... Report performance for the P1,P2,P3,... percentages (0<=P_i<=100, 0 representing max perf, and 100 representing min perf; (default = 90,95,99%) --dumpRefit Print the refittable layers and weights from a refittable engine --dumpOutput Print the output tensor(s) of the last inference iteration (default = disabled) --dumpRawBindingsToFile Print the input/output tensor(s) of the last inference iteration to file(default = disabled) --dumpProfile Print profile information per layer (default = disabled) --dumpLayerInfo Print layer information of the engine to console (default = disabled) --dumpOptimizationProfile Print the optimization profile(s) information (default = disabled) --exportTimes=<file> Write the timing results in a json file (default = disabled) --exportOutput=<file> Write the output tensors to a json file (default = disabled) --exportProfile=<file> Write the profile information per layer in a json file (default = disabled) --exportLayerInfo=<file> Write the layer information of the engine in a json file (default = disabled) === System Options === --device=N Select cuda device N (default = 0) --useDLACore=N Select DLA core N for layers that support DLA (default = none) --staticPlugins Plugin library (.so) to load statically (can be specified multiple times) --dynamicPlugins Plugin library (.so) to load dynamically and may be serialized with the engine if they are included in --setPluginsToSerialize (can be specified multiple times) --setPluginsToSerialize Plugin library (.so) to be serialized with the engine (can be specified multiple times) --ignoreParsedPluginLibs By default, when building a version-compatible engine, plugin libraries specified by the ONNX parser are implicitly serialized with the engine (unless --excludeLeanRuntime is specified) and loaded dynamically. Enable this flag to ignore these plugin libraries instead. --safetyPlugins Plugin library (.so) for TensorRT auto safety to manually load safety plugins specified by the command line arguments. Example: --safetyPlugins=/path/to/plugin_lib.so[pluginNamespace1::plugin1,pluginNamespace2::plugin2]. The option can be specified multiple times with different plugin libraries. === Help === --help, -h Print this message [11/27/2025-14:33:27] [E] Model missing or format not recognized &&&& FAILED TensorRT.trtexec [TensorRT v101401] [b48] # trtexec --version
最新发布
11-28
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值