Meta tags:
description= GPU support for Cloud Run worker pools;
Headings (most frequently used words):
gpu, console, gcloud, support, worker, with, and, supported, pricing, yaml, for, pools, stay, organized, collections, save, categorize, content, based, on, your, preferences, types, regions, impact, zonal, redundancy, options, sla, request, quota, increase, before, you, begin, configure, cloud, run, pool, view, settings, remove, driver, libraries, required, roles, terraform, products, resources, engage,
Text of the page (most frequently used words):
the (165), gpu (121), cloud (111), run (97), #worker (91), and (72), for (64), you (64), with (57), pool (54), nvidia (50), pools (37), your (35), zonal (35), deploy (34), from (33), #redundancy (33), google (32), project (32), memory (29), create (28), cpu (28), container (27), service (25), services (25), overview (25), this (24), are (23), rtx (23), pro (23), 6000 (23), using (22), configure (22), gpus (20), that (19), use (18), blackwell (18), quota (18), gcloud (17), roles (17), configuration (16), code (15), resources (15), following (15), must (15), click (14), select (14), jobs (14), specify (13), worker_pool (13), console (13), can (13), functions (13), image (12), yaml (12), new (12), least (12), page (11), environment (11), view (11), gib (11), region (11), best (11), request (11), build (11), vpc (11), off (10), instance (10), practices (10), samples (9), see (9), replace (9), com (9), containers (9), storage (9), volumes (9), execute (9), function (9), sample (8), need (8), delete (8), gpu_type (8), image_url (8), turn (8), limits (8), turned (8), iam (8), maximum (8), role (8), traffic (8), capacity (8), trigger (8), triggers (8), pricing (7), all (7), thumb (7), more (7), driver (7), default (7), command (7), update (7), existing (7), name (7), networking (7), security (7), value (7), account (7), minimum (7), increase (7), requests (7), pub (7), sub (7), manage (6), details (6), java (6), libraries (6), local (6), number (6), then (6), type (6), enter (6), not (6), reference (6), contains (6), gpu_zonal_redundancy (6), how (6), identity (6), billing (6), enable (6), projects (6), granted (6), cost (6), scaling (6), development (6), tutorial (6), migrate (6), agents (6), metrics (6), python (6), about (5), other (5), which (5), automatically (5), any (5), googleapis (5), settings (5), such (5), resource (5), get (5), access (5), required (5), based (5), note (5), permission (5), when (5), available (5), zones (5), low (5), supported (5), instances (5), application (5), tools (5), migration (5), network (5), source (5), job (5), node (5), eventarc (5), invoke (5), português (4), support (4), contact (4), products (4), down (4), information (4), send (4), version (4), ld_library_path (4), file (4), accelerator (4), remove (4), set (4), configuring (4), menu (4), revision (4), setting (4), interested (4), current (4), docker (4), pkg (4), dev (4), cloudrun (4), latest (4), learn (4), metadata (4), permissions (4), deployment (4), grant (4), usage (4), configurations (4), selector (4), plan (4), selecting (4), resourcemanager (4), require (4), price (4), additional (4), first (4), failover (4), per (4), running (4), asia (4), regions (4), management (4), inference (4), custom (4), direct (4), health (4), variables (4), optimize (4), dependencies (4), sign (3), events (3), understand (3), content (3), under (3), its (3), developers (3), forward (3), compatibility (3), option (3), consult (3), base (3), variable (3), list (3), usr (3), lib64 (3), present (3), nodeselector (3), describe (3), skip (3), checkbox (3), edit (3), lowercase (3), numeric (3), fourteen (3), amount (3), 16gi (3), 80gi (3), terraform (3), one (3), enabled (3), change (3), execution (3), revisions (3), will (3), also (3), make (3), associated (3), apis (3), workerpools (3), created (3), keep (3), specific (3), workloads (3), higher (3), lower (3), needed (3), sla (3), only (3), results (3), multiple (3), zone (3), during (3), might (3), within (3), team (3), europe (3), start (3), demand (3), llm (3), guides (3), hosting (3), frameworks (3), monitoring (3), solutions (3), distributed (3), databases (3), introduction (3), web (3), mcp (3), log (3), write (3), secure (3), authenticate (3), connectors (3), host (3), optimization (3), autoscale (3), labels (3), secrets (3), checks (3), ephemeral (3), disk (3), cifs (3), smb (3), nfs (3), volume (3), mounts (3), entrypoint (3), retries (3), connect (3), firestore (3), concurrent (3), product (3), 한국어 (2), 日本語 (2), עברית (2), brasil (2), italiano (2), indonesia (2), français (2), español (2), américa (2), latina (2), deutsch (2), english (2), our (2), terms (2), site (2), youtube (2), architecture (2), started (2), github (2), system (2), last (2), updated (2), 2026 (2), utc (2), otherwise (2), licensed (2), license (2), feedback (2), cuda (2), than (2), way (2), packages (2), already (2), installed (2), determine (2), provided (2), install (2), path (2), linker (2), defaults (2), format (2), export (2), creating (2), step (2), updating (2), download (2), tab (2), fill (2), out (2), initial (2), expand (2), navigation (2), cli (2), locate (2), cpus (2), true (2), false (2), template (2), commands (2), spec (2), but (2), gpu_number (2), options (2), concurrency (2), recommendations (2), before (2), begin (2), updates (2), user (2), developer (2), recommended (2), scale (2), sure (2), models (2), api (2), likely (2), have (2), through (2), owner (2), serviceusage (2), verify (2), don (2), procedure (2), instead (2), after (2), finish (2), these (2), steps (2), removing (2), creator (2), projectcreator (2), doesn (2), been (2), perform (2), world (2), scenarios (2), free (2), test (2), describes (2), requirements (2), increases (2), without (2), important (2), time (2), non (2), routed (2), sufficient (2), second (2), across (2), affected (2), availability (2), accelerated (2), constraints (2), outage (2), standard (2), healthy (2), provides (2), same (2), priced (2), iowa (2), central1 (2), netherlands (2), west4 (2), singapore (2), southeast1 (2), types (2), attached (2), drivers (2), managed (2), feature (2), work (2), vram (2), documentation (2), sdk (2), languages (2), infrastructure (2), costs (2), observability (2), industry (2), hybrid (2), multicloud (2), data (2), analytics (2), pipelines (2), compute (2), troubleshoot (2), oci (2), app (2), assisted (2), remote (2), server (2), adk (2), a2a (2), logging (2), prometheus (2), controls (2), static (2), shared (2), connector (2), private (2), automate (2), workflows (2), external (2), description (2), systems (2), rollbacks (2), continuous (2), tags (2), timeout (2), tasks (2), testing (2), integrate (2), workflow (2), runtimes (2), images (2), http (2), serving (2), serve (2), git (2), returns (2), php (2), ruby (2), prepare (2), develop (2), cases (2), cross (2), technology (2), areas (2), close (2), subscribe, newsletter, third, decade, climate, action, join, cookies, privacy, tech, twitter, blog, engage, training, certification, center, getting, status, release, notes, community, forums, sales, marketplace, easy, easytounderstand, solved, problem, solvedmyproblem, otherup, hard, hardtounderstand, incorrect, incorrectinformationorsamplecode, missing, missingtheinformationsamplesineed, otherdown, tell, except, noted, registered, trademark, oracle, affiliates, policies, apache, creative, commons, attribution, want, greater, easiest, depend, newer, another, manually, add, them, versions, compatible, matrix, mounted, appends, allows, dynamic, find, searches, resolves, paths, order, values, take, precedence, over, lines, uncheck, returned, open, node_selector, gpu_zonal_redundancy_disabled, location, beta, provider, google_cloud_run_v2_worker_pool, apply, basic, disabled, annotations, workerpool, kind, apiversion, attribute, unspecified, show, check, startup, probe, leads, creation, subsequent, unless, explicit, interfaces, client, granting, guide, serviceaccountuser, ask, administrator, optimal, still, zero, has, building, loading, large, admin, serviceusageadmin, evaluate, real, customers, 300, credits, limitations, requesting, link, made, quickly, links, buttons, milligpus, 000, milligpu, equivalent, depends, whether, uses, refer, attempts, effort, basis, moment, does, guarantee, reserved, reserves, significantly, probability, successfully, handle, rerouted, offering, reliability, failures, outages, specifically, working, mind, mechanism, relies, unused, being, remaining, due, constrained, nature, always, deploys, inherent, resilience, experiences, routes, away, billed, entire, duration, lifecycle, differently, however, sku, cannot, autoscaled, charged, even, process, long, there, difference, between, considerations, impact, northern, virginia, east4, belgium, west1, mumbai, invitation, south1, delhi, india, south2, 535, 580, supports, two, sidecar, pre, approximately, seconds, point, processes, fully, extra, offers, reservations, similar, separate, save, categorize, preferences, stay, organized, collections, home, known, issues, troubleshooting, errors, gke, kubernetes, vmware, tanzu, spring, music, choose, compliant, strategy, foundry, heroku, aws, lambda, 1st, gen, engine, cookbook, vibe, coding, video, transcoding, ffmpeg, batch, fine, tune, llms, hugging, face, transformers, opencv, acceleration, gemma, ollama, browser, automation, servers, n8n, explore, tracing, error, reporting, audit, logs, opentelemetry, built, monitor, multi, tenant, platforms, untrusted, software, supply, chain, insights, customer, encryption, keys, threat, detection, binary, authorization, protect, armor, iap, control, end, authentication, users, audiences, allow, public, design, mesh, restrict, endpoint, ingress, outbound, address, dual, stack, ipv4, ipv6, register, ips, dns, pull, subscriptions, runners, kafka, autoscaler, count, splits, background, checkpoints, stop, executions, task, parallelism, scheduled, completion, event, driven, load, general, tips, grpc, database, entries, processing, into, call, push, subscription, asynchronous, series, part, schedule, asynchronously, websocket, chat, stream, websockets, webhook, target, https, automatic, language, manual, autoscaling, sandboxes, port, recommender, performance, gradual, rollouts, copy, frontend, proxying, nginx, session, affinity, assets, cdn, mapping, domains, compose, sources, codelabs, spanner, bigquery, tutorials, net, compare, package, containerize, shell, sveltekit, nuxt, next, angular, ssr, kotlin, agent, kit, streamlit, smolagents, langchain, gradio, fastapi, flask, hello, repository, should, good, fit, runtime, contract, model, discover, main,
Text of the page (random words):
udiences authenticate developers service to service authenticate users end user authentication tutorial secure your resources access control with iam configure iap for cloud run introduction to service identity protect services with cloud armor use binary authorization use cloud run threat detection use customer managed encryption keys manage custom constraints for projects view software supply chain security insights secure cloud run services tutorial multi tenant platforms running untrusted code monitor and log monitoring and logging overview view built in metrics write prometheus metrics write opentelemetry metrics log and view logs audit logging error reporting use distributed tracing for services run ai solutions overview explore resources ai agents overview build and deploy a2a agents overview deploy a2a agents build and deploy adk agents build and deploy n8n agents mcp servers overview build and deploy a remote mcp server tools code execution browser automation inference with gpus overview services run llm inference on cloud run gpus with ollama run agents with gemma 4 models on cloud run run opencv on cloud run with gpu acceleration run llm inference on cloud run gpus with hugging face transformers js jobs fine tune llms using gpus with cloud run jobs run batch inference using gpus with cloud run jobs gpu accelerated video transcoding with ffmpeg ai assisted development and vibe coding introduction to cloud run for ai assisted developers cookbook migrate an existing web service from app engine from cloud run functions 1st gen from aws lambda from heroku from cloud foundry migration overview choose an oci compliant strategy migrate to oci containers migrate configuration sample migration spring music from vmware tanzu from a vm using migrate to containers from kubernetes to gke troubleshoot introduction troubleshoot errors local troubleshooting tutorial known issues samples all cloud run code samples all cloud run functions code samples code samples for all products ai and ml application development application hosting compute data analytics and pipelines databases distributed hybrid and multicloud industry solutions migration networking observability and monitoring security storage access and resources management costs and usage management infrastructure as code sdk languages frameworks and tools home documentation application hosting cloud run guides send feedback gpu support for worker pools stay organized with collections save and categorize content based on your preferences this page describes gpu configuration for your cloud run workerpools google provides nvidia rtx pro 6000 blackwell gpu with 96 gb of gpu memory vram and nvidia l4 gpus with 24 gb of gpu memory vram which is separate from the instance memory important if you are using llm with the cloud run gpu feature make sure you also consult best practices cloud run workerpools with gpus gpu on cloud run is fully managed with no extra drivers or libraries needed the gpu feature offers on demand availability with no reservations needed similar to the way on demand cpu and on demand memory work in cloud run cloud run instances with an attached nvidia rtx pro 6000 blackwell gpu or l4 gpu with drivers pre installed start in approximately 5 seconds at which point the processes running in your container can start to use the gpu you can configure one gpu per cloud run instance if you use sidecar containers note that the gpu can only be attached to one container supported gpu types cloud run supports two types of gpus nvidia rtx pro 6000 blackwell gpu with the current nvidia driver version 580 x x 13 0 for nvidia rtx pro 6000 blackwell gpu you must use a minimum of 20 cpu and 80 gib of memory l4 gpu with the current nvidia driver version 535 x x 12 2 for l4 gpus you must use a minimum of 4 cpu and 16 gib of memory supported regions the following regions are supported by the nvidia rtx pro 6000 blackwell gpu asia southeast1 singapore asia south2 delhi india europe west4 netherlands low co 2 us central1 iowa low co 2 the following regions are supported by the l4 gpu asia southeast1 singapore asia south1 mumbai this region is available by invitation only contact your google account team if you are interested in this region europe west1 belgium low co 2 europe west4 netherlands low co 2 us central1 iowa low co 2 additional resource scaling in this region might require a quota increase request contact your google account team if you are interested in this region us east4 northern virginia additional resource scaling in this region might require a quota increase request contact your google account team if you are interested in this region pricing impact see cloud run pricing for gpu pricing details note the following requirements and considerations there is a difference in cost between gpu zonal redundancy and non zonal redundancy see cloud run pricing for gpu pricing details gpu worker pools cannot be autoscaled you are charged for the gpu even if the gpu is not running any process and as long as the worker pool gpu instance is running cpu and memory for worker pools is priced differently than services and jobs however gpu sku is priced the same as services and jobs the cpu and memory configurations of your resource gpu is billed for the entire duration of the instance lifecycle gpu zonal redundancy options by default cloud run deploys your worker pool across multiple zones within a region this architecture provides inherent resilience if a zone experiences an outage cloud run automatically routes traffic away from the affected zone to healthy zones within the same region when working with gpu resources keep in mind gpu resources have specific capacity constraints during a zonal outage the standard failover mechanism for gpu workloads relies on sufficient unused gpu capacity being available in the remaining healthy zones due to the constrained nature of gpus this capacity might not always be available to increase the availability of your gpu accelerated worker pools during zonal outages you can configure zonal redundancy specifically for gpus zonal redundancy turned on default cloud run reserves gpu capacity for your worker pool across multiple zones this significantly increases the probability that your worker pool can successfully handle traffic rerouted from an affected zone offering higher reliability during zonal failures with additional cost per gpu second zonal redundancy turned off cloud run attempts failover for gpu workloads on a best effort basis traffic is routed to other zones only if sufficient gpu capacity is available at that moment this option does not guarantee reserved capacity for failover scenarios but results in a lower cost per gpu second sla the sla for cloud run gpu depends on whether the worker pool uses the zonal redundancy or non zonal redundancy option refer to the sla page for details request a quota increase quota for cloud run nvidia rtx pro 6000 gpu is granted in milligpus projects using nvidia rtx pro 6000 gpu in a region for the first time will be automatically granted 3 000 milligpu quota zonal redundancy off when the first deployment is created this is equivalent to 3 gpus projects using cloud run nvidia l4 gpus in a region for the first time are automatically granted 3 gpu quota zonal redundancy off when the first deployment is created if you need additional cloud run gpus you must request a quota increase for your cloud run worker pool use the links provided in the following buttons to request the quota you need important quota increase for gpus with zonal redundancy turned off are more likely to be granted and will be made available more quickly quota needed quota link nvidia rtx pro 6000 blackwell gpu with zonal redundancy turned off lower price request gpu quota without zonal redundancy nvidia rtx pro 6000 blackwell gpu with zonal redundancy turned on higher price request gpu quota with zonal redundancy l4 gpu with zonal redundancy turned off lower price request gpu quota without zonal redundancy l4 gpu with zonal redundancy turned on higher price request gpu quota with zonal redundancy for more information on requesting quota increases see how to increase quota before you begin the following list describes requirements and limitations when using gpus in cloud run sign in to your google cloud account if you re new to google cloud create an account to evaluate how our products perform in real world scenarios new customers also get 300 in free credits to run test and deploy workloads in the google cloud console on the project selector page select or create a google cloud project roles required to select or create a project select a project selecting a project doesn t require a specific iam role you can select any project that you ve been granted a role on create a project to create a project you need the project creator role roles resourcemanager projectcreator which contains the resourcemanager projects create permission learn how to grant roles note if you don t plan to keep the resources that you create in this procedure create a project instead of selecting an existing project after you finish these steps you can delete the project removing all resources associated with the project go to project selector verify that billing is enabled for your google cloud project in the google cloud console on the project selector page select or create a google cloud project roles required to select or create a project select a project selecting a project doesn t require a specific iam role you can select any project that you ve been granted a role on create a project to create a project you need the project creator role roles resourcemanager projectcreator which contains the resourcemanager projects create permission learn how to grant roles note if you don t plan to keep the resources that you create in this procedure create a project instead of selecting an existing project after you finish these steps you can delete the project removing all resources associated with the project go to project selector verify that billing is enabled for your google cloud project enable the cloud run api roles required to enable apis to enable apis you need the serviceusage services enable permission if you created the project then you likely already have this permission through the owner role roles owner otherwise you can get this permission through the service usage admin role roles serviceusage serviceusageadmin learn how to grant roles enable the api request required quota consult gpu best practices cloud run worker pools with gpus for recommendations on building your container image and loading large models make sure your cloud run worker pool has the following configurations configure the billing settings to instance based billing note that worker pools that are set to instance based billing can still scale to zero for nvidia rtx pro 6000 blackwell gpu configure a minimum of 20 cpu and a minimum of 80 gib of memory for l4 gpu configure a minimum of 4 cpu for your worker pool with 8 cpu recommended and a minimum of 16 gib of memory with 32 gib recommended determine and set an optimal maximum concurrency for your gpu usage required roles to get the permissions that you need to configure and deploy cloud run worker pools ask your administrator to grant you the following iam roles on workerpools cloud run developer roles run developer the cloud run worker pool service account user roles iam serviceaccountuser the service identity for a list of iam roles and permissions that are associated with cloud run see cloud run iam roles and cloud run iam permissions if your cloud run worker pool interfaces with google cloud apis such as cloud client libraries see the service identity configuration guide for more information about granting roles see deployment permissions and manage access configure a cloud run worker pool with gpu any configuration change leads to the creation of a new revision subsequent revisions will also automatically get this configuration setting unless you make explicit updates to change it you can use the google cloud console google cloud cli or yaml to configure gpu console in the google cloud console go to cloud run go to cloud run select worker pools from the cloud run navigation menu and click deploy container to configure a new worker pool if you are configuring an existing worker pool click the worker pool then click edit and deploy new revision if you are configuring a new worker pool fill out the initial worker pool settings page then click containers networking security to expand the worker pool configuration page click the container tab configure cpu memory concurrency execution environment and startup probe following the recommendations in before you begin check the gpu checkbox then select the gpu type from the gpu type menu and the number of gpus from the number of gpus menu by default zonal redundancy is turned on to change the current setting select the gpu checkbox to show the gpu redundancy options select no zonal redundancy to turn off zonal redundancy select zonal redundancy to turn on zonal redundancy click create or deploy gcloud to create a gpu enabled worker pool use the gcloud run worker pools deploy command gcloud run worker pools deploy worker_pool image image_url gpu 1 replace the following worker_pool the name of your cloud run worker pool image_url a reference to the container image that contains the worker pool such as us docker pkg dev cloudrun container worker pool latest to update the gpu configuration for a worker pool use the gcloud run worker pools update command gcloud run worker pools update worker_pool image image_url cpu cpu memory memory gpu gpu_number gpu type gpu_type gpu_zonal_redundancy replace the following worker_pool the name of your cloud run worker pool image_url a reference to the container image that contains the worker pool such as us docker pkg dev cloudrun container worker pool latest cpu the number of cpu for nvidia rtx pro 6000 blackwell gpu you must specify at least 20 cpu for nvidia l4 gpu you must specify at least 4 cpu memory the amount of memory for nvidia rtx pro 6000 blackwell gpu you must specify at least 80gi 80 gib for nvidia l4 gpu you must specify at least 16gi 16 gib gpu_number the value 1 one if this is unspecified but a gpu_type is present the default is 1 gpu_type the gpu type nvidia rtx pro 6000 blackwell gpu enter nvidia rtx pro 6000 for l4 gpu enter value nvidia l4 nvidia l 4 lowercase l not numeric value fourteen gpu_zonal_redundancy no gpu zonal redundancy to turn off zonal redundancy or gpu zonal redundancy to turn on zonal redundancy yaml if you are creating a new worker pool skip this step if you are updating an existing worker pool download its yaml configuration gcloud run worker pools describe worker_pool format export worker pool yaml update the nvidia com gpu attribute and nodeselector run googleapis com accelerator apiversion run googleapis c...
|
