From 571279881ce3bddfc7f59b2cc9fd59976b683ce0 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Wed, 24 Jun 2026 10:13:45 -0400 Subject: [PATCH 01/24] lg-Update release-notes-stucture.mdx --- release-notes.mdx | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/release-notes.mdx b/release-notes.mdx index 12f832ce..9ceaaaaa 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -3,8 +3,10 @@ title: "Product updates" sidebarTitle: "Product updates" description: "New features, fixes, and improvements for the Runpod platform." --- - - + + + + ## Flash beta: Run Python functions on cloud GPUs [Flash](/flash/overview) is now in public beta. Flash is a Python SDK that lets you run functions on Runpod Serverless GPUs with a single decorator: @@ -56,9 +58,9 @@ print("Done!") # This runs locally Flash now supports deploying endpoints to [multiple datacenters](/flash/configuration/parameters#datacenter) simultaneously. Pass a list of datacenters to distribute your workload across regions for improved availability and reduced latency. You can also attach [network volumes per datacenter](/flash/configuration/storage#multi-datacenter-volumes) for region-specific data access. - + - + ## New Public Endpoints and expanded examples **[New Public Endpoints](/public-endpoints/reference):** Expansion of available models across all categories. @@ -82,15 +84,17 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - [Run Ollama on Pods](/tutorials/pods/run-ollama): Set up Ollama for LLM inference. - [Build Docker images with Bazel](/tutorials/pods/build-docker-images): Containerize your applications. - + - + ## GitHub release rollback GA and load balancing Serverless repos in beta - [GitHub release rollback](/serverless/workers/github-integration#roll-back-to-a-previous-build): Roll back your Serverless endpoint to any previous build from the console. Restore an earlier version when you encounter issues without waiting for a new GitHub release. - [Load balancing Serverless repos (beta)](/hub/publishing-guide): Load balancing endpoints are now available in the Hub. Publish or convert any listing to load balancer type by setting `"endpointType": "LB"` in your hub.json file, then deploy as a Serverless endpoint or Pod from the Hub page. Maintain a single listing for your model and let users choose their deployment method—autoscaling Serverless or dedicated Pod resources. - + + + ## Pod migration in beta and Serverless development guides From 9002191fdf1ef23aacb8742f8245462c582692f1 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Wed, 24 Jun 2026 10:25:31 -0400 Subject: [PATCH 02/24] Update release-notes.mdx --- release-notes.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/release-notes.mdx b/release-notes.mdx index 9ceaaaaa..a62550a0 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -91,7 +91,7 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - [GitHub release rollback](/serverless/workers/github-integration#roll-back-to-a-previous-build): Roll back your Serverless endpoint to any previous build from the console. Restore an earlier version when you encounter issues without waiting for a new GitHub release. - [Load balancing Serverless repos (beta)](/hub/publishing-guide): Load balancing endpoints are now available in the Hub. Publish or convert any listing to load balancer type by setting `"endpointType": "LB"` in your hub.json file, then deploy as a Serverless endpoint or Pod from the Hub page. Maintain a single listing for your model and let users choose their deployment method—autoscaling Serverless or dedicated Pod resources. - + From 1d49323435ca6a033237a564abd67f03368b4b1a Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Wed, 24 Jun 2026 10:45:15 -0400 Subject: [PATCH 03/24] Update release-notes.mdx --- release-notes.mdx | 50 ++++++++++++++++++++++++++++------------------- 1 file changed, 30 insertions(+), 20 deletions(-) diff --git a/release-notes.mdx b/release-notes.mdx index a62550a0..6560b91b 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -3,6 +3,8 @@ title: "Product updates" sidebarTitle: "Product updates" description: "New features, fixes, and improvements for the Runpod platform." --- + + @@ -95,49 +97,53 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur + - + + + + ## Pod migration in beta and Serverless development guides - [Pod migration (beta)](/references/troubleshooting/pod-migration): Migrate your Pod to a new machine when your stopped Pod's GPU is occupied. Provisions a new Pod with the same specifications and automatically transfers your data to an available machine. - [New Serverless development guides](/serverless/overview): We've added a comprehensive new set of guides for developing, testing, and debugging Serverless endpoints. - + - + ## Slurm Clusters GA, cached models in beta, and new Public Endpoints available - [Slurm Clusters are now generally available](/instant-clusters/slurm-clusters): Deploy production-ready HPC clusters in seconds. These clusters support multi-node performance for distributed training and large-scale simulations with pay-as-you-go billing and no idle costs. - [Cached models are now in beta](/serverless/endpoints/model-caching): Eliminate model download times when starting workers. The system places cached models on host machines before workers start, prioritizing hosts with your model already available for instant startup. - [New Public Endpoints available](/public-endpoints/overview): [WAN 2.5](/public-endpoints/models/wan-2-5) combines image and audio to create lifelike videos, while [Nano Banana](/public-endpoints/models/nano-banana-edit) merges multiple images for composite creations. - + - + ## Hub revenue sharing launches and Pods UI gets refreshed - [Hub revenue share model](/hub/revenue-sharing): Publish to the Runpod Hub and earn credits when others deploy your repo. Earn up to 7% of compute revenue through monthly tiers with credits auto-deposited into your account. - [Pods UI updated](/pods/overview): Refreshed modern interface for interacting with Runpod Pods. - + - + ## Public Endpoints arrive, Slurm Clusters in beta - [Public Endpoints](/public-endpoints/overview): Access state-of-the-art AI models through simple API calls with an integrated playground. Available endpoints include [Qwen Image Edit](/public-endpoints/models/qwen-image-edit), [Flux Kontext](/public-endpoints/models/flux-kontext-dev), [Cogito 671B](/public-endpoints/models/cogito-671b), and [Minimax Speech](/public-endpoints/models/minimax-speech). - [Slurm Clusters (beta)](/instant-clusters/slurm-clusters): Create on-demand multi-node clusters instantly with full Slurm scheduling support. - + - + ## S3-compatible storage and updated referral program - [S3-compatible API for network volumes](/storage/s3-api): Upload and retrieve files from your network volumes without compute using AWS S3 CLI or Boto3. Integrate Runpod storage into any AI pipeline with zero-config ease and object-level control. - [Referral program revamp](/references/referrals): Updated rewards and tiers with clearer dashboards to track performance. - + - + ## Port labeling, price drops, Runpod Hub, and Tetra beta test - [Port labeling](/pods/overview): Name exposed ports in the UI and API to help team members identify services like Jupyter or TensorBoard. @@ -145,18 +151,18 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - [Runpod Hub](/hub/overview): A curated catalog of one-click endpoints and templates for deploying community projects without starting from scratch. - **Tetra beta test**: A Python library for running code on GPU with Runpod. Add a `@remote()` decorator to functions that need GPU power while the rest of your code runs locally. - + - + ## GitHub login, RTX 5090s, and global networking expansion - **Login with GitHub**: OAuth sign-in and linking for faster onboarding and repo-driven workflows. - **RTX 5090s on Runpod**: High-performance RTX 5090 availability for cost-efficient training and inference. - [Global networking expansion](/pods/networking): Rollout to additional data centers approaching full global coverage. - + - + ## Enterprise features arrive, REST API goes GA, Instant Clusters in beta, and APAC expansion - [CPU Pods get network storage access](/storage/network-volumes): GA support for network volumes on CPU Pods for persistent, shareable storage. @@ -166,25 +172,29 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - **Bare metal**: Reserve dedicated GPU servers for maximum control, performance, and long-term savings. - **AP-JP-1**: New Fukushima region for low-latency APAC access and in-country data residency. - + - + ## REST API enters beta with full-time community manager - [REST API beta test](/api-reference/overview): RESTful endpoints for Pods, endpoints, and volumes for simpler automation than GraphQL. - **Full-time community manager hire**: Dedicated programs, content, and faster community response. - [Serverless GitHub integration release](/serverless/workers/github-integration): GA for GitHub-based Serverless deploys with production-ready stability. - + - + ## New silicon and LLM-focused Serverless upgrades - **CPU Pods v2**: Docker runtime parity with GPU Pods for faster starts with network volume support. - [H200s on Runpod](/references/gpu-types): NVIDIA H200 GPUs available for larger models and higher memory bandwidth. - [Serverless upgrades](/serverless/overview): Higher GPU counts per worker, new quick-deploy runtimes, and simpler model selection. - + + + + + ## Global networking expands and GitHub deploys enter beta From 3a1746c9015e1072852d4dc67bceca633c54f879 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Wed, 24 Jun 2026 11:00:10 -0400 Subject: [PATCH 04/24] Update release-notes.mdx --- release-notes.mdx | 81 +++++++++++++++++++++++++---------------------- 1 file changed, 44 insertions(+), 37 deletions(-) diff --git a/release-notes.mdx b/release-notes.mdx index 6560b91b..ff9703eb 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -6,8 +6,6 @@ description: "New features, fixes, and improvements for the Runpod platform." - - ## Flash beta: Run Python functions on cloud GPUs @@ -95,12 +93,10 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - [Load balancing Serverless repos (beta)](/hub/publishing-guide): Load balancing endpoints are now available in the Hub. Publish or convert any listing to load balancer type by setting `"endpointType": "LB"` in your hub.json file, then deploy as a Serverless endpoint or Pod from the Hub page. Maintain a single listing for your model and let users choose their deployment method—autoscaling Serverless or dedicated Pod resources. - - ## Pod migration in beta and Serverless development guides @@ -192,11 +188,12 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - - + + + ## Global networking expands and GitHub deploys enter beta - [Global networking expansion](/pods/networking): Added to CA-MTL-3, US-GA-1, US-GA-2, and US-KS-2 for expanded private mesh coverage. @@ -204,26 +201,26 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - **Scoped API keys**: Least-privilege tokens with fine-grained scopes and expirations for safer automation. - **Passkey auth**: Passwordless WebAuthn sign-in for phishing-resistant account access. - + - + ## Storage expansion and private cross-data-center connectivity - [US-GA-2 added to network storage](/storage/network-volumes): Enable network volumes in US-GA-2. - [Global networking](/pods/networking): Private cross-data-center networking with internal DNS for secure service-to-service traffic. - + - + ## Storage coverage grows with major price cuts and revamped referrals - **US-TX-3 and EUR-IS-1 added to network storage**: Network volumes available in more regions for local persistence. - **Runpod slashes GPU prices**: Broad GPU price reductions to lower training and inference total cost of ownership. - [Referral program revamp](/references/referrals): Updated commissions and bonuses with an affiliate tier and improved tracking. - + - + ## $20M seed round, community event, and broader Serverless options - **$20M seed by Intel Capital and Dell Technologies Capital**: Funds infrastructure expansion and product acceleration. @@ -231,26 +228,30 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - [Serverless CPU Pods](/references/cpu-types): Scale-to-zero CPU endpoints for services that don't need a GPU. - [AMD GPUs](/references/gpu-types): AMD ROCm-compatible GPU SKUs as cost and performance alternatives to NVIDIA. - + - + ## CPU compute and first-class automation tooling - **CPU Pods**: CPU-only instances with the same networking and storage primitives for cheaper non-GPU stages. - [runpodctl](/runpodctl/overview): Official CLI for Pods, endpoints, and volumes to enable scripting and CI/CD workflows. - + - + ## Console navigation overhaul and documentation refresh - **New navigational changes to Runpod UI**: Consolidated menus, consistent action placement, and fewer clicks for common tasks. - **Docs revamp**: New information architecture, improved search, and more runnable examples and quickstarts. - **Zhen AMA**: Roadmap Q&A and community feedback session. - + + + - + + + ## New regions and investment in community support - **US-OR-1**: Additional US region for lower latency and more capacity in the Pacific Northwest. @@ -258,18 +259,18 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - **First community manager hire**: Dedicated community programs and faster feedback loops. - **Building out the support team**: Expanded coverage and expertise for complex issues. - + - + ## Faster template starts and better multi-region hygiene - **Serverless quick deploy**: One-click deploy of curated model templates with sensible defaults. - **EU domain for Serverless**: EU-specific domain briefly offered for data residency, superseded by other region controls. - **Data-center filter for Serverless**: Filter and manage endpoints by region for multi-region fleets. - + - + ## Self-service upgrades, clearer metrics, new pricing model, and cost visibility - **Self-service worker upgrade**: Rebuild and roll workers from the dashboard without support tickets. @@ -278,9 +279,9 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - [Flex and active workers](/serverless/pricing): Always-on "active" workers for baseline load with on-demand "flex" workers for bursts. - **Billing explorer**: Inspect costs by resource, region, and time to identify optimization opportunities. - + - + ## Team governance, storage expansion, and better debugging - [Teams](/get-started/manage-accounts): Organization workspaces with role-based access control for Pods, endpoints, and billing. @@ -290,27 +291,27 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - **Serverless health endpoint**: Lightweight /health probe returning endpoint and worker status without creating a billable job. - **SOC 2 Type II compliant**: Security and compliance certification for enterprise customers. - + - + ## Observability, top-tier GPUs, and commitment-based savings - **Serverless metrics page**: Time-series charts for pXX latencies, queue delay, throughput, and worker states for faster debugging and tuning. - [H100s on Runpod](/references/gpu-types): NVIDIA H100 instances for higher throughput and larger model footprints. - [Savings plans](/pods/pricing): Commitment-based discounts for predictable workloads to lower effective hourly rates. - + - + ## Smoother auth and multi-region Serverless with persistent storage - **The new and improved Runpod login experience**: Streamlined sign-in and team access for faster, more consistent auth flows. - [Network volumes added to Serverless](/storage/network-volumes): Attach persistent storage to Serverless workers to retain models and artifacts across restarts and speed cold starts through caching. - **Serverless region support**: Pin or allow specific regions for endpoints to reduce latency and meet data-residency needs. - + - + ## Deeper autoscaling controls, richer metrics, persistent storage, and job cancellation - **Serverless scaling strategies**: Scale by queue delay and/or concurrency with min/max worker bounds to balance latency and cost. @@ -320,26 +321,32 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - **Network storage beta**: Region-scoped, attachable volumes shareable across Pods and endpoints for model caches and datasets. - **Job cancel API**: Programmatically terminate queued or running jobs to free capacity and enforce client timeouts. - + - + ## Serverless platform hardens with cleaner API - **Serverless API v2**: Revised request and response schema with improved error semantics and new endpoints for better control over job lifecycle and observability. - + - + ## Better control over notifications and GPU allocation - **Notification preferences**: Configure which platform events trigger alerts to reduce noise for teams and CI systems. - **GPU priorities**: Influence scheduling by marking workloads as higher priority to reduce queue time for critical jobs. - + + - + + + ## Encrypted volumes for persistent data - **Runpod now offers encrypted volumes**: Enable at-rest encryption for persistent volumes with no application changes required using platform-managed keys. - + + + + From 245d1a2440009a32161ad0d85fdd0f23e61fba65 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Wed, 24 Jun 2026 11:03:25 -0400 Subject: [PATCH 05/24] Update release-notes.mdx --- release-notes.mdx | 1 - 1 file changed, 1 deletion(-) diff --git a/release-notes.mdx b/release-notes.mdx index ff9703eb..2585b2ce 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -93,7 +93,6 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - [Load balancing Serverless repos (beta)](/hub/publishing-guide): Load balancing endpoints are now available in the Hub. Publish or convert any listing to load balancer type by setting `"endpointType": "LB"` in your hub.json file, then deploy as a Serverless endpoint or Pod from the Hub page. Maintain a single listing for your model and let users choose their deployment method—autoscaling Serverless or dedicated Pod resources. - From ba6125783e0f867a4b7607ea3754272a40e418f9 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Wed, 24 Jun 2026 11:05:02 -0400 Subject: [PATCH 06/24] Update release-notes.mdx --- release-notes.mdx | 1 + 1 file changed, 1 insertion(+) diff --git a/release-notes.mdx b/release-notes.mdx index 2585b2ce..0ce71f1d 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -337,6 +337,7 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur + From ab29adc9efed1497513fe9ba4a9c1b9557ecab75 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Wed, 24 Jun 2026 11:06:57 -0400 Subject: [PATCH 07/24] Update release-notes.mdx --- release-notes.mdx | 1 - 1 file changed, 1 deletion(-) diff --git a/release-notes.mdx b/release-notes.mdx index 0ce71f1d..5660530e 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -188,7 +188,6 @@ Flash now supports deploying endpoints to [multiple datacenters](/flash/configur - From acdf2828647f7ed986457605812218ee87de2958 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Wed, 24 Jun 2026 11:21:56 -0400 Subject: [PATCH 08/24] Update release-notes.mdx --- release-notes.mdx | 3 +++ 1 file changed, 3 insertions(+) diff --git a/release-notes.mdx b/release-notes.mdx index 5660530e..27e05579 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -3,6 +3,9 @@ title: "Product updates" sidebarTitle: "Product updates" description: "New features, fixes, and improvements for the Runpod platform." --- + + We've updated our release notes format for easier navigation. Updates from April 2026 onwards are listed above. Browse earlier releases by year and month in the archive below. + From d3519d595a563cb96420d82e877ca5dadaeb9f8f Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Wed, 24 Jun 2026 11:30:52 -0400 Subject: [PATCH 09/24] Update release-notes.mdx --- release-notes.mdx | 85 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 85 insertions(+) diff --git a/release-notes.mdx b/release-notes.mdx index 27e05579..44d9a231 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -3,6 +3,91 @@ title: "Product updates" sidebarTitle: "Product updates" description: "New features, fixes, and improvements for the Runpod platform." --- + + + + ## Savings Plan IDOR vulnerability fixed + + A security issue allowed Savings Plan data to be accessible across organizations without authorization. The query is now scoped to the authenticated owner. No user action is required. + + ## High-Performance Network Volumes now available + + A new high-performance storage tier is available for [Pods, Serverless endpoints, and Instant Clusters](/storage/network-volumes). Reduces model load times significantly compared to standard network volumes. Identifiable by the purple diamond icon on compatible datacenters. + + ## ECR Integration now in beta + + You can now pull private container images from AWS ECR into [Pods and Serverless endpoints](/pods/overview) without migrating registries or working around credentials. ECR delegation is available in beta. + + ## Hub navigation consolidated + + All Hub nav items are now merged into one unified navigation entry, reducing clutter and making it faster to find templates and repos. + + ## Billing records now show correct data for deleted resources + + SKU, region, and creation timestamps were missing from billing records when a Pod or network volume had been deleted. These fields now appear correctly across all [billing views and exports](/pods/pricing). + + ## Savings Plans discontinued + + Savings Plans have been sunset and removed from the product. Existing plans were honored through their term. [Cost Centers](/get-started/manage-accounts) and on-demand pricing are the recommended path forward for cost management. + + + + ## Async Jobs for Serverless + + Submit a payload to a [Serverless endpoint](/serverless/overview) and retrieve the result when capacity is available — no always-on workers burning credits between requests, no polling loops. Jobs are queued and processed automatically when a worker is free. + + ## Serverless Worker Fitness Checks + + Serverless workers now run automated health checks before accepting jobs. Unhealthy workers are removed from rotation automatically, reducing failed requests and improving endpoint reliability. + + ## Deploy When Available + + Request a GPU that's currently out of capacity and get notified by email when it becomes available. Your pod configuration is saved so you can deploy immediately when capacity returns — no need to check back manually. + + ## 24GB MiG instances now available + + High-end GPUs (H100 and RTX PRO 6000) can now be partitioned into up to seven independent [24GB MiG instances](/references/gpu-types). Expands available supply and gives you more granular, lower-cost GPU access without reserving a full card. + + ## Cost Centers now generally available + + [Cost Centers](/get-started/manage-accounts) let teams allocate and track GPU spend by project, team, or business unit. Detailed cost breakdowns are now available in billing, and all users receive itemized invoices as of May 1. + + ## New Pod deploy flow — workload-first GPU selection + + The Pod deployment experience has been redesigned. Instead of picking a GPU first, you now choose a template or workload type and get recommended GPUs ranked as recommended, compatible, or incompatible. Includes Save as Template, AI-assisted GPU selection, and a Notify Me When Available option for out-of-capacity cards. + + ## Active Worker discount reduced from 30% to 15% + + The always-on [Active Worker discount](/serverless/pricing) has been reduced from 30% to 15%. Flex workers remain unaffected. Review your endpoint configuration if you rely on Active Workers for baseline load. + + + + ## Flash is now generally available + + [Flash](/flash/overview) exits beta and is now GA. Run Python functions on cloud GPUs with a single `@Endpoint` decorator — no containers, no infra setup. Workers scale automatically, dependencies install on remote workers, and you can deploy production APIs with `flash deploy`. The fastest path from local code to GPU-backed inference. + + ## Instant Cluster Expansion and Priority FlashBoot now live + + [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster than before. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. + + ## FlashBoot for CPU Serverless now in public beta + + CPU Serverless workers now support FlashBoot, dramatically reducing cold-start times for CPU endpoints. GA planned later this quarter. + + ## Efficient Cluster Expansion + + Adding nodes to an [Instant Cluster](/instant-clusters/overview) no longer requires manual GraphQL queries or database operations. Admins can now scale clusters quickly and reliably through automated host-managed networking. Existing clusters were migrated without incident. + + ## GPU price reductions across popular SKUs + + Prices have been reduced across a range of GPU SKUs, lowering the cost of training and inference workloads. Updated pricing is reflected in the console and [pricing page](/pods/pricing). + + ## Serverless GPU exclusions now correctly respected + + GPU type exclusions set on Serverless endpoints were not being enforced, causing workloads to land on excluded GPU types and incorrect billing. The issue has been fixed and new alerting added to detect recurrence. + + + We've updated our release notes format for easier navigation. Updates from April 2026 onwards are listed above. Browse earlier releases by year and month in the archive below. From 59bd4cedeea7f46bfadb392e10c89d85f8313209 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Wed, 24 Jun 2026 11:31:43 -0400 Subject: [PATCH 10/24] Update release-notes.mdx --- release-notes.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/release-notes.mdx b/release-notes.mdx index 44d9a231..bf3d2735 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -86,7 +86,7 @@ description: "New features, fixes, and improvements for the Runpod platform." GPU type exclusions set on Serverless endpoints were not being enforced, causing workloads to land on excluded GPU types and incorrect billing. The issue has been fixed and new alerting added to detect recurrence. - + We've updated our release notes format for easier navigation. Updates from April 2026 onwards are listed above. Browse earlier releases by year and month in the archive below. From dca10a9dfcf57ea099112b24eda6a6840160743d Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Wed, 24 Jun 2026 11:45:53 -0400 Subject: [PATCH 11/24] Update release-notes.mdx --- release-notes.mdx | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/release-notes.mdx b/release-notes.mdx index bf3d2735..5155d9c8 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -6,83 +6,83 @@ description: "New features, fixes, and improvements for the Runpod platform." - ## Savings Plan IDOR vulnerability fixed + ## Savings Plan IDOR vulnerability fixed Security A security issue allowed Savings Plan data to be accessible across organizations without authorization. The query is now scoped to the authenticated owner. No user action is required. - ## High-Performance Network Volumes now available + ## High-Performance Network Volumes now available New Release A new high-performance storage tier is available for [Pods, Serverless endpoints, and Instant Clusters](/storage/network-volumes). Reduces model load times significantly compared to standard network volumes. Identifiable by the purple diamond icon on compatible datacenters. - ## ECR Integration now in beta + ## ECR Integration now in beta New Release You can now pull private container images from AWS ECR into [Pods and Serverless endpoints](/pods/overview) without migrating registries or working around credentials. ECR delegation is available in beta. - ## Hub navigation consolidated + ## Hub navigation consolidated Improvement All Hub nav items are now merged into one unified navigation entry, reducing clutter and making it faster to find templates and repos. - ## Billing records now show correct data for deleted resources + ## Billing records now show correct data for deleted resources Bug Fix SKU, region, and creation timestamps were missing from billing records when a Pod or network volume had been deleted. These fields now appear correctly across all [billing views and exports](/pods/pricing). - ## Savings Plans discontinued + ## Savings Plans discontinued Deprecated Savings Plans have been sunset and removed from the product. Existing plans were honored through their term. [Cost Centers](/get-started/manage-accounts) and on-demand pricing are the recommended path forward for cost management. - ## Async Jobs for Serverless + ## Async Jobs for Serverless New Release Submit a payload to a [Serverless endpoint](/serverless/overview) and retrieve the result when capacity is available — no always-on workers burning credits between requests, no polling loops. Jobs are queued and processed automatically when a worker is free. - ## Serverless Worker Fitness Checks + ## Serverless Worker Fitness Checks New Release Serverless workers now run automated health checks before accepting jobs. Unhealthy workers are removed from rotation automatically, reducing failed requests and improving endpoint reliability. - ## Deploy When Available + ## Deploy When Available New Release Request a GPU that's currently out of capacity and get notified by email when it becomes available. Your pod configuration is saved so you can deploy immediately when capacity returns — no need to check back manually. - ## 24GB MiG instances now available + ## 24GB MiG instances now available New Release High-end GPUs (H100 and RTX PRO 6000) can now be partitioned into up to seven independent [24GB MiG instances](/references/gpu-types). Expands available supply and gives you more granular, lower-cost GPU access without reserving a full card. - ## Cost Centers now generally available + ## Cost Centers now generally available New Release [Cost Centers](/get-started/manage-accounts) let teams allocate and track GPU spend by project, team, or business unit. Detailed cost breakdowns are now available in billing, and all users receive itemized invoices as of May 1. - ## New Pod deploy flow — workload-first GPU selection + ## New Pod deploy flow — workload-first GPU selection Improvement The Pod deployment experience has been redesigned. Instead of picking a GPU first, you now choose a template or workload type and get recommended GPUs ranked as recommended, compatible, or incompatible. Includes Save as Template, AI-assisted GPU selection, and a Notify Me When Available option for out-of-capacity cards. - ## Active Worker discount reduced from 30% to 15% + ## Active Worker discount reduced from 30% to 15% Improvement The always-on [Active Worker discount](/serverless/pricing) has been reduced from 30% to 15%. Flex workers remain unaffected. Review your endpoint configuration if you rely on Active Workers for baseline load. - ## Flash is now generally available + ## Flash is now generally available New Release [Flash](/flash/overview) exits beta and is now GA. Run Python functions on cloud GPUs with a single `@Endpoint` decorator — no containers, no infra setup. Workers scale automatically, dependencies install on remote workers, and you can deploy production APIs with `flash deploy`. The fastest path from local code to GPU-backed inference. - ## Instant Cluster Expansion and Priority FlashBoot now live + ## Instant Cluster Expansion and Priority FlashBoot now live New Release [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster than before. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. - ## FlashBoot for CPU Serverless now in public beta + ## FlashBoot for CPU Serverless now in public beta New Release CPU Serverless workers now support FlashBoot, dramatically reducing cold-start times for CPU endpoints. GA planned later this quarter. - ## Efficient Cluster Expansion + ## Efficient Cluster Expansion Improvement Adding nodes to an [Instant Cluster](/instant-clusters/overview) no longer requires manual GraphQL queries or database operations. Admins can now scale clusters quickly and reliably through automated host-managed networking. Existing clusters were migrated without incident. - ## GPU price reductions across popular SKUs + ## GPU price reductions across popular SKUs Improvement Prices have been reduced across a range of GPU SKUs, lowering the cost of training and inference workloads. Updated pricing is reflected in the console and [pricing page](/pods/pricing). - ## Serverless GPU exclusions now correctly respected + ## Serverless GPU exclusions now correctly respected Bug Fix GPU type exclusions set on Serverless endpoints were not being enforced, causing workloads to land on excluded GPU types and incorrect billing. The issue has been fixed and new alerting added to detect recurrence. From 837eda2f137467ae496805b3bd52e74018a9ee28 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Fri, 26 Jun 2026 15:17:50 -0400 Subject: [PATCH 12/24] Update docs.json --- docs.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs.json b/docs.json index ef888bd3..3bce3642 100644 --- a/docs.json +++ b/docs.json @@ -32,7 +32,7 @@ "navigation": { "tabs": [ { - "tab": "Docs", + "tab": h1 { font-size: 2.5rem; }, "Docs", "groups": [ { "group": "Get started", From 3a368ed6b4e3bea2fe172e728123c6396cacef87 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 15:01:19 -0400 Subject: [PATCH 13/24] Update release-notes.mdx --- release-notes.mdx | 90 ++++++++++++++++++++++------------------------- 1 file changed, 42 insertions(+), 48 deletions(-) diff --git a/release-notes.mdx b/release-notes.mdx index 5155d9c8..c62f5074 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -5,87 +5,81 @@ description: "New features, fixes, and improvements for the Runpod platform." --- - - ## Savings Plan IDOR vulnerability fixed Security + + ## High-Performance Network Volumes now available New Release - A security issue allowed Savings Plan data to be accessible across organizations without authorization. The query is now scoped to the authenticated owner. No user action is required. + You can now attach high-performance network volumes to [Pods, Serverless endpoints, and Instant Clusters](/storage/network-volumes) for significantly faster model load times. Look for the purple diamond icon to identify compatible datacenters. - ## High-Performance Network Volumes now available New Release + ## ECR Integration now in beta New Release - A new high-performance storage tier is available for [Pods, Serverless endpoints, and Instant Clusters](/storage/network-volumes). Reduces model load times significantly compared to standard network volumes. Identifiable by the purple diamond icon on compatible datacenters. + You can now pull private container images from AWS ECR into [Pods and Serverless endpoints](/pods/overview) without migrating registries or managing credentials. ECR delegation is available in beta. - ## ECR Integration now in beta New Release + ## Deploy When Available New Release - You can now pull private container images from AWS ECR into [Pods and Serverless endpoints](/pods/overview) without migrating registries or working around credentials. ECR delegation is available in beta. + You can now request a GPU that's currently out of capacity and get notified by email when it becomes available. Runpod saves your pod configuration so you can deploy immediately when capacity returns. - ## Hub navigation consolidated Improvement + ## Hub navigation consolidated Improvement - All Hub nav items are now merged into one unified navigation entry, reducing clutter and making it faster to find templates and repos. + Hub navigation items are now consolidated into a single unified entry, making it easier to find templates and repos. - ## Billing records now show correct data for deleted resources Bug Fix + ## Billing records now show correct data for deleted resources Bug Fix - SKU, region, and creation timestamps were missing from billing records when a Pod or network volume had been deleted. These fields now appear correctly across all [billing views and exports](/pods/pricing). + SKU, region, and creation timestamps now appear correctly in [billing views and exports](/pods/pricing) for deleted Pods and network volumes. - ## Savings Plans discontinued Deprecated + ## Savings Plans discontinued Deprecated - Savings Plans have been sunset and removed from the product. Existing plans were honored through their term. [Cost Centers](/get-started/manage-accounts) and on-demand pricing are the recommended path forward for cost management. - + We've paused Savings Plans. No new plans can be purchased, and existing ones were honored through their full term. We're exploring what cost-saving options look like going forward, so stay tuned for updates. In the meantime, [Cost Centers](/get-started/manage-accounts) are the best way to manage and track your GPU spend. + + + ## Async Jobs for Serverless New Release - - ## Async Jobs for Serverless New Release + You can now submit a job to a [Serverless endpoint](/serverless/overview) and retrieve the result asynchronously when capacity is available. Jobs queue and process automatically when a worker is free, with no always-on workers or polling loops required. - Submit a payload to a [Serverless endpoint](/serverless/overview) and retrieve the result when capacity is available — no always-on workers burning credits between requests, no polling loops. Jobs are queued and processed automatically when a worker is free. + ## Serverless Worker Fitness Checks New Release - ## Serverless Worker Fitness Checks New Release + Serverless workers now run automated health checks before accepting jobs. Runpod automatically removes unhealthy workers from rotation, reducing failed requests and improving endpoint reliability. - Serverless workers now run automated health checks before accepting jobs. Unhealthy workers are removed from rotation automatically, reducing failed requests and improving endpoint reliability. + ## 24GB MiG instances now available New Release - ## Deploy When Available New Release + You can now partition H100 and RTX PRO 6000 GPUs into up to seven independent [24GB MiG instances](/references/gpu-types), giving you more granular, lower-cost access without reserving a full card. - Request a GPU that's currently out of capacity and get notified by email when it becomes available. Your pod configuration is saved so you can deploy immediately when capacity returns — no need to check back manually. + ## Cost Centers now generally available New Release - ## 24GB MiG instances now available New Release + [Cost Centers](/get-started/manage-accounts) let teams allocate and track GPU spend by project, team, or business unit. Detailed cost breakdowns are now available in billing, and all users receive itemized invoices as of May 1. - High-end GPUs (H100 and RTX PRO 6000) can now be partitioned into up to seven independent [24GB MiG instances](/references/gpu-types). Expands available supply and gives you more granular, lower-cost GPU access without reserving a full card. + ## New Pod deploy flow with workload-first GPU selection Improvement - ## Cost Centers now generally available New Release + The Pod deployment experience has been redesigned. Instead of picking a GPU first, you now choose a template or workload type and get recommended GPUs ranked as recommended, compatible, or incompatible. The new flow includes Save as Template, AI-assisted GPU selection, and a Notify Me When Available option for out-of-capacity cards. - [Cost Centers](/get-started/manage-accounts) let teams allocate and track GPU spend by project, team, or business unit. Detailed cost breakdowns are now available in billing, and all users receive itemized invoices as of May 1. + ## Active Worker discount reduced from 30% to 15% Improvement - ## New Pod deploy flow — workload-first GPU selection Improvement + The always-on [Active Worker discount](/serverless/pricing) has been reduced from 30% to 15%. Flex workers remain unaffected. Review your endpoint configuration if you rely on Active Workers for baseline load. + + + ## Flash is now generally available New Release - The Pod deployment experience has been redesigned. Instead of picking a GPU first, you now choose a template or workload type and get recommended GPUs ranked as recommended, compatible, or incompatible. Includes Save as Template, AI-assisted GPU selection, and a Notify Me When Available option for out-of-capacity cards. + [Flash](/flash/overview) is now generally available. You can run Python functions on cloud GPUs with a single `@Endpoint` decorator, with no containers or infrastructure setup required. Workers scale automatically, dependencies install on remote workers, and you can deploy production APIs with `flash deploy`. - ## Active Worker discount reduced from 30% to 15% Improvement + ## Instant Cluster Expansion and Priority FlashBoot now live New Release - The always-on [Active Worker discount](/serverless/pricing) has been reduced from 30% to 15%. Flex workers remain unaffected. Review your endpoint configuration if you rely on Active Workers for baseline load. - + [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. - - ## Flash is now generally available New Release + ## FlashBoot for CPU Serverless now in public beta New Release - [Flash](/flash/overview) exits beta and is now GA. Run Python functions on cloud GPUs with a single `@Endpoint` decorator — no containers, no infra setup. Workers scale automatically, dependencies install on remote workers, and you can deploy production APIs with `flash deploy`. The fastest path from local code to GPU-backed inference. + CPU Serverless workers now support FlashBoot, dramatically reducing cold-start times for your CPU endpoints. GA is planned for later this quarter. - ## Instant Cluster Expansion and Priority FlashBoot now live New Release + ## Efficient Cluster Expansion Improvement - [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster than before. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. + You can now add nodes to an [Instant Cluster](/instant-clusters/overview) without manual GraphQL queries or database operations. Automated host-managed networking lets admins scale clusters quickly and reliably. Existing clusters were migrated without incident. - ## FlashBoot for CPU Serverless now in public beta New Release + ## GPU price reductions across popular SKUs Improvement - CPU Serverless workers now support FlashBoot, dramatically reducing cold-start times for CPU endpoints. GA planned later this quarter. + GPU prices have been reduced across a range of SKUs, lowering the cost of your training and inference workloads. Updated pricing is reflected in the console and [pricing page](/pods/pricing). - ## Efficient Cluster Expansion Improvement + ## Serverless GPU exclusions now correctly respected Bug Fix - Adding nodes to an [Instant Cluster](/instant-clusters/overview) no longer requires manual GraphQL queries or database operations. Admins can now scale clusters quickly and reliably through automated host-managed networking. Existing clusters were migrated without incident. - - ## GPU price reductions across popular SKUs Improvement - - Prices have been reduced across a range of GPU SKUs, lowering the cost of training and inference workloads. Updated pricing is reflected in the console and [pricing page](/pods/pricing). - - ## Serverless GPU exclusions now correctly respected Bug Fix - - GPU type exclusions set on Serverless endpoints were not being enforced, causing workloads to land on excluded GPU types and incorrect billing. The issue has been fixed and new alerting added to detect recurrence. - + GPU type exclusions set on Serverless endpoints were not being enforced, causing workloads to land on excluded GPU types and resulting in incorrect billing. The issue is now fixed, and new alerting has been added to detect recurrence. + From 00c0741ab2c4a686c0a36f211a2ee19198acd426 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 15:12:27 -0400 Subject: [PATCH 14/24] Update docs.json --- docs.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs.json b/docs.json index 3bce3642..ef888bd3 100644 --- a/docs.json +++ b/docs.json @@ -32,7 +32,7 @@ "navigation": { "tabs": [ { - "tab": h1 { font-size: 2.5rem; }, "Docs", + "tab": "Docs", "groups": [ { "group": "Get started", From 186aa22982251178527038fe959e847b0d0798de Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 15:19:05 -0400 Subject: [PATCH 15/24] Update release-notes.mdx --- release-notes.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/release-notes.mdx b/release-notes.mdx index c62f5074..ec18987a 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -26,7 +26,7 @@ description: "New features, fixes, and improvements for the Runpod platform." SKU, region, and creation timestamps now appear correctly in [billing views and exports](/pods/pricing) for deleted Pods and network volumes. - ## Savings Plans discontinued Deprecated + ## Savings Plans temporarily paused Deprecated We've paused Savings Plans. No new plans can be purchased, and existing ones were honored through their full term. We're exploring what cost-saving options look like going forward, so stay tuned for updates. In the meantime, [Cost Centers](/get-started/manage-accounts) are the best way to manage and track your GPU spend. From 3881d2bf8cff4fe63c658ba7b6295ab652c25a5a Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 15:45:21 -0400 Subject: [PATCH 16/24] Update release-notes.mdx --- release-notes.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/release-notes.mdx b/release-notes.mdx index ec18987a..6d52c57b 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -62,7 +62,7 @@ description: "New features, fixes, and improvements for the Runpod platform." ## Instant Cluster Expansion and Priority FlashBoot now live New Release - [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. + [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. Reach out to your FDE or account manager for more details and to request expansions. ## FlashBoot for CPU Serverless now in public beta New Release From 144992fb8fdb8205920a962923bfef08613626ac Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 17:50:05 -0400 Subject: [PATCH 17/24] Update release-notes.mdx --- release-notes.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/release-notes.mdx b/release-notes.mdx index 6d52c57b..48dfac40 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -62,7 +62,7 @@ description: "New features, fixes, and improvements for the Runpod platform." ## Instant Cluster Expansion and Priority FlashBoot now live New Release - [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. Reach out to your FDE or account manager for more details and to request expansions. + [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. Expanding an existing cluster is currently only available to Runpod admins. Reach out to your FDE or account manager for more details and to request expansions. ## FlashBoot for CPU Serverless now in public beta New Release From 9e84f123536d8d1684af985838e602302c1f6c0c Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 22:28:32 -0400 Subject: [PATCH 18/24] Update release-notes.mdx --- release-notes.mdx | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/release-notes.mdx b/release-notes.mdx index 48dfac40..d3358575 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -25,10 +25,7 @@ description: "New features, fixes, and improvements for the Runpod platform." ## Billing records now show correct data for deleted resources Bug Fix SKU, region, and creation timestamps now appear correctly in [billing views and exports](/pods/pricing) for deleted Pods and network volumes. - - ## Savings Plans temporarily paused Deprecated - - We've paused Savings Plans. No new plans can be purchased, and existing ones were honored through their full term. We're exploring what cost-saving options look like going forward, so stay tuned for updates. In the meantime, [Cost Centers](/get-started/manage-accounts) are the best way to manage and track your GPU spend. + ## Async Jobs for Serverless New Release @@ -49,11 +46,8 @@ description: "New features, fixes, and improvements for the Runpod platform." ## New Pod deploy flow with workload-first GPU selection Improvement - The Pod deployment experience has been redesigned. Instead of picking a GPU first, you now choose a template or workload type and get recommended GPUs ranked as recommended, compatible, or incompatible. The new flow includes Save as Template, AI-assisted GPU selection, and a Notify Me When Available option for out-of-capacity cards. - - ## Active Worker discount reduced from 30% to 15% Improvement - - The always-on [Active Worker discount](/serverless/pricing) has been reduced from 30% to 15%. Flex workers remain unaffected. Review your endpoint configuration if you rely on Active Workers for baseline load. + The Pod deployment experience has been redesigned. Instead of picking a GPU first, you now choose a template or workload type and get recommended GPUs ranked as recommended, compatible, or incompatible. The new flow includes Save as Template, AI-assisted GPU selection, and a Notify Me When Available option for out-of-capacity cards. + ## Flash is now generally available New Release @@ -68,10 +62,6 @@ description: "New features, fixes, and improvements for the Runpod platform." CPU Serverless workers now support FlashBoot, dramatically reducing cold-start times for your CPU endpoints. GA is planned for later this quarter. - ## Efficient Cluster Expansion Improvement - - You can now add nodes to an [Instant Cluster](/instant-clusters/overview) without manual GraphQL queries or database operations. Automated host-managed networking lets admins scale clusters quickly and reliably. Existing clusters were migrated without incident. - ## GPU price reductions across popular SKUs Improvement GPU prices have been reduced across a range of SKUs, lowering the cost of your training and inference workloads. Updated pricing is reflected in the console and [pricing page](/pods/pricing). From 795d346d00214aa910bef392b6d122bfd1bf28dd Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 22:58:44 -0400 Subject: [PATCH 19/24] Update release-notes.mdx --- release-notes.mdx | 66 ++++++++++++++++++++++++++++------------------- 1 file changed, 40 insertions(+), 26 deletions(-) diff --git a/release-notes.mdx b/release-notes.mdx index d3358575..ca9cc8b9 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -3,70 +3,84 @@ title: "Product updates" sidebarTitle: "Product updates" description: "New features, fixes, and improvements for the Runpod platform." --- +{/* ## ECR Integration now in beta New Release + + You can now pull private container images from AWS ECR into [Pods and Serverless endpoints](/pods/overview) without migrating registries or managing credentials. ECR delegation is available in beta. + */} - ## High-Performance Network Volumes now available New Release - - You can now attach high-performance network volumes to [Pods, Serverless endpoints, and Instant Clusters](/storage/network-volumes) for significantly faster model load times. Look for the purple diamond icon to identify compatible datacenters. - - ## ECR Integration now in beta New Release - - You can now pull private container images from AWS ECR into [Pods and Serverless endpoints](/pods/overview) without migrating registries or managing credentials. ECR delegation is available in beta. + New Release + ## High-Performance Network Volumes now available - ## Deploy When Available New Release + You can now attach high-performance network volumes to [Pods, Serverless endpoints, and Instant Clusters](/storage/network-volumes) for significantly faster model load times. Look for the purple diamond icon to identify compatible datacenters. + + New Release + ## Deploy When Available You can now request a GPU that's currently out of capacity and get notified by email when it becomes available. Runpod saves your pod configuration so you can deploy immediately when capacity returns. - ## Hub navigation consolidated Improvement + Improvement + ## Hub navigation consolidated Hub navigation items are now consolidated into a single unified entry, making it easier to find templates and repos. - - ## Billing records now show correct data for deleted resources Bug Fix + + Bug Fix + ## Billing records now show correct data for deleted resources SKU, region, and creation timestamps now appear correctly in [billing views and exports](/pods/pricing) for deleted Pods and network volumes. - ## Async Jobs for Serverless New Release + New Release + ## Async Jobs for Serverless You can now submit a job to a [Serverless endpoint](/serverless/overview) and retrieve the result asynchronously when capacity is available. Jobs queue and process automatically when a worker is free, with no always-on workers or polling loops required. - - ## Serverless Worker Fitness Checks New Release + + New Release + ## Serverless Worker Fitness Checks Serverless workers now run automated health checks before accepting jobs. Runpod automatically removes unhealthy workers from rotation, reducing failed requests and improving endpoint reliability. - - ## 24GB MiG instances now available New Release + + New Release + ## 24GB MiG instances now available You can now partition H100 and RTX PRO 6000 GPUs into up to seven independent [24GB MiG instances](/references/gpu-types), giving you more granular, lower-cost access without reserving a full card. - - ## Cost Centers now generally available New Release + + New Release + ## Cost Centers now generally available [Cost Centers](/get-started/manage-accounts) let teams allocate and track GPU spend by project, team, or business unit. Detailed cost breakdowns are now available in billing, and all users receive itemized invoices as of May 1. - - ## New Pod deploy flow with workload-first GPU selection Improvement + + Improvement + ## New Pod deploy flow with workload-first GPU selection The Pod deployment experience has been redesigned. Instead of picking a GPU first, you now choose a template or workload type and get recommended GPUs ranked as recommended, compatible, or incompatible. The new flow includes Save as Template, AI-assisted GPU selection, and a Notify Me When Available option for out-of-capacity cards. - ## Flash is now generally available New Release + New Release + ## Flash is now generally available [Flash](/flash/overview) is now generally available. You can run Python functions on cloud GPUs with a single `@Endpoint` decorator, with no containers or infrastructure setup required. Workers scale automatically, dependencies install on remote workers, and you can deploy production APIs with `flash deploy`. - ## Instant Cluster Expansion and Priority FlashBoot now live New Release + New Release + ## Instant Cluster Expansion and Priority FlashBoot now live [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. Expanding an existing cluster is currently only available to Runpod admins. Reach out to your FDE or account manager for more details and to request expansions. - - ## FlashBoot for CPU Serverless now in public beta New Release + + New Release + ## FlashBoot for CPU Serverless now in public beta CPU Serverless workers now support FlashBoot, dramatically reducing cold-start times for your CPU endpoints. GA is planned for later this quarter. - ## GPU price reductions across popular SKUs Improvement + Improvement + ## GPU price reductions across popular SKUs GPU prices have been reduced across a range of SKUs, lowering the cost of your training and inference workloads. Updated pricing is reflected in the console and [pricing page](/pods/pricing). - ## Serverless GPU exclusions now correctly respected Bug Fix + Bug Fix + ## Serverless GPU exclusions now correctly respected GPU type exclusions set on Serverless endpoints were not being enforced, causing workloads to land on excluded GPU types and resulting in incorrect billing. The issue is now fixed, and new alerting has been added to detect recurrence. From 7c0aeb315aaa66cf27a67e3e87c3e9791779bb6b Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 23:04:04 -0400 Subject: [PATCH 20/24] Update release-notes.mdx --- release-notes.mdx | 43 +++++++++++++++---------------------------- 1 file changed, 15 insertions(+), 28 deletions(-) diff --git a/release-notes.mdx b/release-notes.mdx index ca9cc8b9..1eb92743 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -2,6 +2,7 @@ title: "Product updates" sidebarTitle: "Product updates" description: "New features, fixes, and improvements for the Runpod platform." +mode: "wide" --- {/* ## ECR Integration now in beta New Release @@ -10,77 +11,63 @@ description: "New features, fixes, and improvements for the Runpod platform." - New Release - ## High-Performance Network Volumes now available + New Release### High-Performance Network Volumes now available You can now attach high-performance network volumes to [Pods, Serverless endpoints, and Instant Clusters](/storage/network-volumes) for significantly faster model load times. Look for the purple diamond icon to identify compatible datacenters. - New Release - ## Deploy When Available + New Release### Deploy When Available You can now request a GPU that's currently out of capacity and get notified by email when it becomes available. Runpod saves your pod configuration so you can deploy immediately when capacity returns. - Improvement - ## Hub navigation consolidated + Improvement### Hub navigation consolidated Hub navigation items are now consolidated into a single unified entry, making it easier to find templates and repos. - Bug Fix - ## Billing records now show correct data for deleted resources + Bug Fix### Billing records now show correct data for deleted resources SKU, region, and creation timestamps now appear correctly in [billing views and exports](/pods/pricing) for deleted Pods and network volumes. - New Release - ## Async Jobs for Serverless + New Release### Async Jobs for Serverless You can now submit a job to a [Serverless endpoint](/serverless/overview) and retrieve the result asynchronously when capacity is available. Jobs queue and process automatically when a worker is free, with no always-on workers or polling loops required. - New Release - ## Serverless Worker Fitness Checks + New Release### Serverless Worker Fitness Checks Serverless workers now run automated health checks before accepting jobs. Runpod automatically removes unhealthy workers from rotation, reducing failed requests and improving endpoint reliability. - New Release - ## 24GB MiG instances now available + New Release### 24GB MiG instances now available You can now partition H100 and RTX PRO 6000 GPUs into up to seven independent [24GB MiG instances](/references/gpu-types), giving you more granular, lower-cost access without reserving a full card. - New Release - ## Cost Centers now generally available + New Release### Cost Centers now generally available [Cost Centers](/get-started/manage-accounts) let teams allocate and track GPU spend by project, team, or business unit. Detailed cost breakdowns are now available in billing, and all users receive itemized invoices as of May 1. - Improvement - ## New Pod deploy flow with workload-first GPU selection + Improvement### New Pod deploy flow with workload-first GPU selection The Pod deployment experience has been redesigned. Instead of picking a GPU first, you now choose a template or workload type and get recommended GPUs ranked as recommended, compatible, or incompatible. The new flow includes Save as Template, AI-assisted GPU selection, and a Notify Me When Available option for out-of-capacity cards. - New Release - ## Flash is now generally available + New Release### Flash is now generally available [Flash](/flash/overview) is now generally available. You can run Python functions on cloud GPUs with a single `@Endpoint` decorator, with no containers or infrastructure setup required. Workers scale automatically, dependencies install on remote workers, and you can deploy production APIs with `flash deploy`. - New Release - ## Instant Cluster Expansion and Priority FlashBoot now live + New Release### Instant Cluster Expansion and Priority FlashBoot now live [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. Expanding an existing cluster is currently only available to Runpod admins. Reach out to your FDE or account manager for more details and to request expansions. - New Release - ## FlashBoot for CPU Serverless now in public beta + New Release### FlashBoot for CPU Serverless now in public beta CPU Serverless workers now support FlashBoot, dramatically reducing cold-start times for your CPU endpoints. GA is planned for later this quarter. - Improvement - ## GPU price reductions across popular SKUs + Improvement### GPU price reductions across popular SKUs GPU prices have been reduced across a range of SKUs, lowering the cost of your training and inference workloads. Updated pricing is reflected in the console and [pricing page](/pods/pricing). - Bug Fix - ## Serverless GPU exclusions now correctly respected + Bug Fix### Serverless GPU exclusions now correctly respected GPU type exclusions set on Serverless endpoints were not being enforced, causing workloads to land on excluded GPU types and resulting in incorrect billing. The issue is now fixed, and new alerting has been added to detect recurrence. From effd7785c4f44c4f7b401ebb6bdbfa3a7c5f5d6c Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 23:06:26 -0400 Subject: [PATCH 21/24] Update release-notes.mdx --- release-notes.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/release-notes.mdx b/release-notes.mdx index 1eb92743..e2ba8783 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -11,7 +11,7 @@ mode: "wide" - New Release### High-Performance Network Volumes now available + New Release ### High-Performance Network Volumes now available You can now attach high-performance network volumes to [Pods, Serverless endpoints, and Instant Clusters](/storage/network-volumes) for significantly faster model load times. Look for the purple diamond icon to identify compatible datacenters. From cb6fafbb52488e4f9de85e9355ac1e14def83527 Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 23:11:14 -0400 Subject: [PATCH 22/24] Update release-notes.mdx --- release-notes.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/release-notes.mdx b/release-notes.mdx index e2ba8783..5cc675c3 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -11,7 +11,7 @@ mode: "wide" - New Release ### High-Performance Network Volumes now available +

New Release High-Performance Network Volumes now available

You can now attach high-performance network volumes to [Pods, Serverless endpoints, and Instant Clusters](/storage/network-volumes) for significantly faster model load times. Look for the purple diamond icon to identify compatible datacenters. From f5bc5ea3fe0216719f5a032cd1416cd5baf90cab Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 23:16:15 -0400 Subject: [PATCH 23/24] Update release-notes.mdx --- release-notes.mdx | 77 ++++++++++++++++++++++++----------------------- 1 file changed, 40 insertions(+), 37 deletions(-) diff --git a/release-notes.mdx b/release-notes.mdx index 5cc675c3..0dffd76c 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -11,64 +11,67 @@ mode: "wide" -

New Release High-Performance Network Volumes now available

- - You can now attach high-performance network volumes to [Pods, Serverless endpoints, and Instant Clusters](/storage/network-volumes) for significantly faster model load times. Look for the purple diamond icon to identify compatible datacenters. - New Release### Deploy When Available - +

New Release High-Performance Network Volumes now available

+ + You can now attach high-performance network volumes to [Pods, Serverless endpoints, and Instant Clusters](/storage/network-volumes) for significantly faster model load times. Look for the purple diamond icon to identify compatible datacenters. + +

New Release Deploy When Available

+ You can now request a GPU that's currently out of capacity and get notified by email when it becomes available. Runpod saves your pod configuration so you can deploy immediately when capacity returns. - - Improvement### Hub navigation consolidated - + +

Improvement Hub navigation consolidated

+ Hub navigation items are now consolidated into a single unified entry, making it easier to find templates and repos. - Bug Fix### Billing records now show correct data for deleted resources - +

Bug Fix Billing records now show correct data for deleted resources

+ SKU, region, and creation timestamps now appear correctly in [billing views and exports](/pods/pricing) for deleted Pods and network volumes. - + - New Release### Async Jobs for Serverless - + +

New Release Async Jobs for Serverless

+ You can now submit a job to a [Serverless endpoint](/serverless/overview) and retrieve the result asynchronously when capacity is available. Jobs queue and process automatically when a worker is free, with no always-on workers or polling loops required. - New Release### Serverless Worker Fitness Checks - +

New Release Serverless Worker Fitness Checks

+ Serverless workers now run automated health checks before accepting jobs. Runpod automatically removes unhealthy workers from rotation, reducing failed requests and improving endpoint reliability. - New Release### 24GB MiG instances now available - +

New Release 24GB MiG instances now available

+ You can now partition H100 and RTX PRO 6000 GPUs into up to seven independent [24GB MiG instances](/references/gpu-types), giving you more granular, lower-cost access without reserving a full card. - New Release### Cost Centers now generally available - +

New Release Cost Centers now generally available

+ [Cost Centers](/get-started/manage-accounts) let teams allocate and track GPU spend by project, team, or business unit. Detailed cost breakdowns are now available in billing, and all users receive itemized invoices as of May 1. - Improvement### New Pod deploy flow with workload-first GPU selection - - The Pod deployment experience has been redesigned. Instead of picking a GPU first, you now choose a template or workload type and get recommended GPUs ranked as recommended, compatible, or incompatible. The new flow includes Save as Template, AI-assisted GPU selection, and a Notify Me When Available option for out-of-capacity cards. - +

Improvement New Pod deploy flow with workload-first GPU selection

+ + The Pod deployment experience has been redesigned. Instead of picking a GPU first, you now choose a template or workload type and get recommended GPUs ranked as recommended, compatible, or incompatible. The new flow includes Save as Template, AI-assisted GPU selection, and a Notify Me When Available option for out-of-capacity cards. + - New Release### Flash is now generally available - + +

New Release Flash is now generally available

+ [Flash](/flash/overview) is now generally available. You can run Python functions on cloud GPUs with a single `@Endpoint` decorator, with no containers or infrastructure setup required. Workers scale automatically, dependencies install on remote workers, and you can deploy production APIs with `flash deploy`. - - New Release### Instant Cluster Expansion and Priority FlashBoot now live - - [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. Expanding an existing cluster is currently only available to Runpod admins. Reach out to your FDE or account manager for more details and to request expansions. - New Release### FlashBoot for CPU Serverless now in public beta - +

New Release Instant Cluster Expansion and Priority FlashBoot now live

+ + [Instant Clusters](/instant-clusters/overview) can now expand to more nodes faster. Priority FlashBoot reduces cold-start times for cluster workers. Both features are live with no configuration changes needed. Expanding an existing cluster is currently only available to Runpod admins. To add nodes to an existing cluster, reach out to the Runpod team. + +

New Release FlashBoot for CPU Serverless now in public beta

+ CPU Serverless workers now support FlashBoot, dramatically reducing cold-start times for your CPU endpoints. GA is planned for later this quarter. - - Improvement### GPU price reductions across popular SKUs - + +

Improvement GPU price reductions across popular SKUs

+ GPU prices have been reduced across a range of SKUs, lowering the cost of your training and inference workloads. Updated pricing is reflected in the console and [pricing page](/pods/pricing). - - Bug Fix### Serverless GPU exclusions now correctly respected - + +

Bug Fix Serverless GPU exclusions now correctly respected

+ GPU type exclusions set on Serverless endpoints were not being enforced, causing workloads to land on excluded GPU types and resulting in incorrect billing. The issue is now fixed, and new alerting has been added to detect recurrence. From 2fef3c75f1da95128f8952735d44058ac6af442f Mon Sep 17 00:00:00 2001 From: lgunreddi Date: Mon, 29 Jun 2026 23:17:48 -0400 Subject: [PATCH 24/24] Update release-notes.mdx --- release-notes.mdx | 1 - 1 file changed, 1 deletion(-) diff --git a/release-notes.mdx b/release-notes.mdx index 0dffd76c..71ae0c5c 100644 --- a/release-notes.mdx +++ b/release-notes.mdx @@ -2,7 +2,6 @@ title: "Product updates" sidebarTitle: "Product updates" description: "New features, fixes, and improvements for the Runpod platform." -mode: "wide" --- {/* ## ECR Integration now in beta New Release