24.03.7b3

Fixes

• Fix BACKEND_MODEL_NAME environment always overwritten to model name specified at model definition (#2481)
• Do not allow assigning preopen port which collides with image's own service port definition (#2482)
• Fix GET requests with queryparams defined in API spec occasionally throwing 400 Bad Request error (#2483)

Full Changelog

Check out the full changelog until this release (24.03.7b3).

Full Commit Logs

Check out the full commit logs between release (24.03.7b2) and (24.03.7b3).

24.03.7b2

Fixes

• Fix incorrect check of values returned from docker stat API. (#2389)
• Handle all possible exceptions when scheduling single node session so that the status information of pending session is not empty. (#2411)
• Improve error handling of initialization failures in the kernel runner (#2478)

Full Changelog

Check out the full changelog until this release (24.03.7b2).

Full Commit Logs

Check out the full commit logs between release (24.03.7b1) and (24.03.7b2).

24.03.7b1

Features

• Add row_id, type and container_registry fields to the GroupNode GQL schema. (#2409)
• Add support for PureStorage RapidFiles Toolkit v2 (#2419)

Improvements

• Remove database-level foreign key constraints in vfolders.{user,group} columns to decouple the timing of vfolder deletion and user/group deletion. (#2404)

Fixes

• Add missing commit_session_to_file to OP_EXC (#2127)
• Pass ImageRef.canonical in commit_session_to_file (#2134)
• Omit to clean containerless kernels which are still creating its container. (#2317)
• Run batch execution after the batch session starts. (#2327)
• Add support for configuring sync_container_lifecycles() task. (#2338)
• Restrict GraphQL query to user_nodes field to require superadmin privilege (#2401)
• Utilize ExtendedJSONEncoder for error logging to handle UUID objects in extra_data (#2415)
• Change outdated references in event module from kernels to sessions. (#2421)
• Upgrade inquirer to remove dependency on deprecated distutils, which breaks up execution of the scie builds (#2424)
• Allow specific status of vfolders to query to purge. (#2429)
• Update the install-dev scripts to use pnpm instead of npm to speed up installation and resolve some peculiar version resolution issues related to esbuild. (#2436)
• Fix a packaging issue in the backendai-webserver scie executable due to missing explicit requirement of setuptools (#2454)
• Improve pruning of non-physical filesystems when measuring disk usage in agents (#2460)

External Dependency Updates

• Upgrade aiodocker to 0.22.1 to fix error handling when trying to extract the log of non-existing containers (#2402)
• Upgrade the base CPython from 3.12.2 to 3.12.4 (#2449)

Miscellaneous

• Handle container creation exception and start exception in separate try-except contexts. (#2316)

Full Changelog

Check out the full changelog until this release (24.03.7b1).

Full Commit Logs

Check out the full commit logs between release (24.03.7a2) and (24.03.7b1).

24.03.7a2

Features

• Add support for fetching container logs of a specific kernel. (#2364)

Fixes

• Fix buggy resolver of model_card GQL Query. (#2161)
• Keep sync_container_lifecycles() bgtask alive in a loop. (#2178)
• Shutdown agent properly by removing a code that waits a cancelled task. (#2392)

Miscellaneous

• Finally stabilize the hanging tests in our CI due to docker-internal races on TCP port mappings to concurrently spawned fixture containers by introducing monotonically increasing TCP port numbers (#2379)
• Further improve the monotonic port allocation logic for the test containers to remove maximum concurrency restrictions (#2396)

Full Changelog

Check out the full changelog until this release (24.03.7a2).

Full Commit Logs

Check out the full commit logs between release (24.03.7a1) and (24.03.7a2).

24.03.7a1

Features

• Allow superadmins to force-update session status through destroy API. (#2275)
• Introduce Python native WSProxy (#2372)

Fixes

• Fix user creation error when any model-store does not exists. (#2160)
• Ensure that utilization idleness is checked after a set period. (#2205)
• Fix ZeroDivisionError in volume usage calculation by returning 0% when volume capacity is zero (#2245)
• Fix GraphQL to support query to non-installed images (#2250)
• Add missing push_image method implementation to Dummy Agent (#2253)
• Corrected an issue where the resource_policy field in the user model was incorrectly mapped to domain_name. (#2314)
• Fix mismatches between responses of /services/_runtimes and new model service creation input (#2371)

External Dependency Updates

• Upgrade aiodocker to v0.22.0 with minor bug fixes found by improved type annotations (#2339)

Full Changelog

Check out the full changelog until this release (24.03.7a1).

Full Commit Logs

Check out the full commit logs between release (24.03.6) and (24.03.7a1).

24.03.6

Fixes

• Fix model service sessions created before 24.03.5 failing to spawn (#2318)
• Image commit not working (#2319)
• model service session scheduler (scale_services()) failing when sessions bound to active route already marked as terminated (#2320)
• Fix container metric collection halted on systems with Cgroups v1 (#2321)

Full Changelog

Check out the full changelog until this release (24.03.6).

Full Commit Logs

Check out the full commit logs between release (24.03.5) and (24.03.6).

24.03.5

Features

• New redis client (experimental) (#2041)
• Add support for CentOS 8 based kernels (#2220)
• Allow modifying model service session's environment variable setup (#2255)
• Add endpoint.runtime_variant column (#2256)
• Add new API to show list of supported inference runtimes (#2258)
• Add support for model service provisioning without model-definition.yaml (#2260)

Fixes

• Do not omit to update session's occupying resources to DB when a kernel starts. (#1832)
• Rename no-op access_key parameter of endpoint_list GQL Query to user_uuid (#2287)
• Fix ai.backend.service-ports label syntax broken when image does not expose built-in service port (#2288)
• Improve stability of untag_image_from_registry mutation (#2289)
• SSH not working between kernels started with customized image (#2290)
• Invalid container memory capacity reported (#2291)

Full Changelog

Check out the full changelog until this release (24.03.5).

Full Commit Logs

Check out the full commit logs between release (24.03.5rc1) and (24.03.5).

24.03.5rc1

No significant changes.

Full Changelog

Check out the full changelog until this release (24.03.5rc1).

Full Commit Logs

Check out the full commit logs between release (24.03.5b1) and (24.03.5rc1).

24.03.5b1

Features

• New redis client (experimental) (#2041)
• Add support for CentOS 8 based kernels (#2220)
• Allow modifying model service session's environment variable setup (#2255)
• Add endpoint.runtime_variant column (#2256)
• Add new API to show list of supported inference runtimes (#2258)
• Add support for model service provisioning without model-definition.yaml (#2260)

Fixes

• Do not omit to update session's occupying resources to DB when a kernel starts. (#1832)
• Rename no-op access_key parameter of endpoint_list GQL Query to user_uuid (#2287)
• Fix ai.backend.service-ports label syntax broken when image does not expose built-in service port (#2288)
• Improve stability of untag_image_from_registry mutation (#2289)
• SSH not working between kernels started with customized image (#2290)
• Invalid container memory capacity reported (#2291)

Full Changelog

Check out the full changelog until this release (24.03.5b1).

Full Commit Logs

Check out the full commit logs between release (24.03.4) and (24.03.5b1).

24.03.4

Features

• Allow user to explicitly set filename of model definition YAML (#2063)
• Revamp images GQL query by changing image filtering from flag-based to feature set-based and add aliases field to customized image GQL schema (#2136)
• Added missing fields for keypair_resource_policy in client-py, models, etc. (#2146)
• Add parameters to check-presets SDK function (#2153)
• Add relay-aware VirtualFolderNode GQL Query (#2165)
• Also perform basic model service validation process when updating model service via ModifyEndpoint (#2167)
• Add support for mounting arbitrary VFolders on model service session (#2168)
• Clear zombie routes automatically (#2229)

Fixes

• Let the backend.ai mgr clear-history command clears session records as well as kernel records (#2077)
• Fix orphan model service routes being created (#2096)
• Fix initialization of the resource usage API's kernel-level usage aggregation (#2102)
• Fix model server starting on every kernels (including sub role kernels) on multi container infernce session (#2124)
• Handle fileset-already-exists response of create-filset API request and make sure to wait between all GPFS job polling iterations (#2144)
• • Fix error when calling check_presets Client SDK API with an invalid group parameter
  • Rewrite Client SDK to access all APIConfig fields (#2152)
• Ensure that all pending sessions are picked by schedulers (#2155)
• Fix security vulnerability for sudo_session_enabled (#2162)
• Rename endpoints.model_mount_destiation to model_mount_destination (#2163)
• Wait for real quota scope directory creation after Netapp create_qtree() call (#2170)
• Fix wrong per-user concurrency calculation logic (#2175)
• Fix model service persisting on degraded status forever in rare chance when trying to delete the service (#2191)
• Fix error when query or mutate GraphQL using BigInt field type (#2203)
• Fix backend.ai ssh command execution when packaged as SCIE/PEX (#2226)
• • fix endpoints query not working when trying to load image_row.aliases
  • fix endpoints.status reporting PROVISIONING when its status is in DESTROYING state (#2233)
• Fix GQL raising error when trying to resolve endpoints.errors field occasionally (#2236)

Miscellaneous

• Fix incorrect version notation of GQL Field. (#1993)
• Add max_pending_session_count field to Keypair resource policy GQL schema (#2013)

Full Changelog

Check out the full changelog until this release (24.03.4).

Full Commit Logs

Check out the full commit logs between release (24.03.4rc1) and (24.03.4).