Commit Graph
16411 Commits
Author SHA1 Message Date
屈轩 df94e8049b fix(yunionconf): batch import tags (#25116) 2026-07-09 16:43:01 +08:00
Jian QiuandQiu Jian 7651726458 fix: host order by sql redundant group by (#25114)
Co-authored-by: Qiu Jian <qiujian@yunionyun.com>
2026-07-09 14:22:44 +08:00
cwz_eikoh 52d2ddcb45 feat(aiproxy): support log record in aiproxy through minio (#25078) 2026-07-09 13:01:21 +08:00
Jian QiuandQiu Jian 54b7c42d94 fix: lb listener rule specific certificates (#25106)
Co-authored-by: Qiu Jian <qiujian@yunionyun.com>
2026-07-08 12:03:53 +08:00
Zexi Li 167682c39b feat(aiproxy): add Anthropic Messages API and migrate functional tests to Go (#25107)
Add /v1/messages handler with Anthropic-to-OpenAI translation, upstream
failover, and probe endpoints. Replace shell-based functional test scripts
with pkg/aiproxy/ft and climc test commands; consolidate documentation.
2026-07-07 20:13:14 +08:00
屈轩 e6c9393955 fix(region): pve host driver compatibility (#25098) 2026-07-03 15:37:40 +08:00
Zexi Li 9cc4d76a81 feat(llm): add ModelScope instant model import and refactor model download (#25092)
Add ModelScope hub integration, download driver, and instant model import
flow parallel to HuggingFace. Extract shared HuggingFace download helpers
and reuse them across vLLM/SGLang container drivers.
2026-07-01 20:13:17 +08:00
Zexi Li 3431c10196 feat(llm): support local_path scheduling with prefer_hosts and deployment restart (#25090) 2026-07-01 13:11:19 +08:00
wanyaoqi 31e342881e fix(host-deployer): mount procfs before deploy guestfs (#25087) 2026-07-01 00:53:59 +08:00
Zexi Li 0f63315fc8 feat(scheduler): append GPU reserved resource hints on predicate failure (#25084) 2026-06-30 15:40:50 +08:00
Zexi Li d9cf601841 feat(llm): backfill orphan LLM instances into deployments on init (#25081)
On service startup, find LLM instances without llm_deployment_id and
create a matching SLLMDeployment, then link the instance. Idempotent
across restarts; skipped on slave nodes.
2026-06-29 11:28:54 +08:00
wanyaoqi 1b742b49e9 fix(host-deployer): do base64 windows password (#25071) 2026-06-28 08:24:48 +08:00
屈轩 7802f909e0 fix(region): quota check (#25066) 2026-06-26 13:06:00 +08:00
wanyaoqi 75cc892bf7 fix(region,host): kvm guest change disk driver reset uefi vars (#25069) 2026-06-26 10:20:37 +08:00
wanyaoqi be57fc2845 fix(host): qemu set multifd before start incoming migration (#25065)
use drive mirror do block migration
2026-06-26 10:18:58 +08:00
cwz_eikoh b48c1be667 feat(llm): tool call defaults & auto gpu ultilization (#25074)
* feat(llm): upgrade auto-gpu-ultilization

* feat(llm): add vllm tool call defaults

* feat(llm): add sglang tool call defaults
2026-06-26 10:15:19 +08:00
Zexi Li 8f1d740b54 feat(llm): async instant model delete and improve import status tracking (#25073)
fix(aiproxy): set OpenAI handler process timeouts and skip upstream error
response when request context is already cancelled.
2026-06-25 19:52:46 +08:00
Zexi Li ba39e80fd8 feat(llm): validate GPU devices on deployment create and improve error messages (#25063) 2026-06-24 14:27:25 +08:00
wanyaoqi 143ca823c8 fix(region): snapshot validate add check guest is quorum master guest (#25051) 2026-06-24 10:30:00 +08:00
cwz_eikoh d4dd65cb24 Feature/http get+llm probe (#25016)
* hostman: probe http get in pod netns

* llm: watch pod status for service readiness
2026-06-23 19:40:30 +08:00
屈轩 e693162ad0 fix(region): filter sku by zone ids (#25060) 2026-06-23 15:00:30 +08:00
Zexi Li f69856eeb0 fix(aiproxy): defer stream context cancel until chunks are consumed (#25059) 2026-06-23 14:09:47 +08:00
Zexi Li 4a4b3f8676 feat(llm): sync llm deployment with aiproxy catalog and routing (#25057)
Add auto_register_aiproxy on llm_deployment creation, background sync task,
and register/unregister CLI actions. Link aiproxy providers, routings, and
models to llm replicas via llm_id and llm_deployment_id fields.
2026-06-22 20:14:01 +08:00
cwz_eikoh 108db8ca87 Feature/llm route for aiproxy (#25044)
* feat(aiproxy): support routing model in aiproxy

* feat(llm): add llm-router
2026-06-22 10:09:38 +08:00
Jian QiuandQiu Jian 50a7105cff fix: credential scope revisit (#25049)
Co-authored-by: Qiu Jian <qiujian@yunionyun.com>
2026-06-21 08:34:50 +08:00
wanyaoqi ba9a7fe775 fix(host): recycle servers dir on guest delete (#25021) 2026-06-21 08:34:07 +08:00
Jian QiuandQiu Jian 6fa7c8f9d2 fix: some host_type should consider container (#25047)
Co-authored-by: Qiu Jian <qiujian@yunionyun.com>
2026-06-20 09:47:32 +08:00
屈轩 2b927e742d fix(region): remove debug log (#25041) 2026-06-17 14:50:20 +08:00
屈轩 8a6d6faf24 fix(region): aws dedicated host sync (#25039) 2026-06-16 20:14:23 +08:00
屈轩andCursor 8719e73105 fix(compute): polish httperrors error messages in pkg/compute (#25035)
Unify spelling, grammar, and semantics of API error strings without changing error types or business logic.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-15 20:49:16 +08:00
Zexi Li 3ff72d8a38 feat(llm): add community images catalog API (#25032)
Expose llmimages.yaml as list/show/refresh endpoints with configurable
source URL, periodic cache refresh, and mcclient module support.
2026-06-15 17:26:37 +08:00
屈轩 24caa8dd11 fix(region): filter sku by zone ids (#25028) 2026-06-15 15:50:42 +08:00
屈轩 bd236cb965 fix(region): vendor update (#25026) 2026-06-15 14:58:10 +08:00
屈轩 7d0870790a fix(region): struct tag fix (#25023) 2026-06-15 11:04:17 +08:00
wanyaoqi f36d39848c fix(region): guest detach isolated devices add is_force options (#25019) 2026-06-15 09:54:29 +08:00
屈轩 bf919b8f7a fix(region): disk througput sync (#25017) 2026-06-13 11:54:43 +08:00
wanyaoqi 6126af72d4 fix(host): guest python launcher error (#25014) 2026-06-12 14:07:35 +08:00
屈轩 688ae49a28 fix(region): optimized sku query (#25008) 2026-06-11 14:31:21 +08:00
wanyaoqi 44f7c6e688 fix(region): host model add api stats (#24956) 2026-06-09 23:02:04 +08:00
屈轩 7c7353cf7b feat(aiproxy): add aiproxy (#24916) 2026-06-09 18:54:42 +08:00
屈轩 e9a6034705 fix(region): sku price (#25001) 2026-06-09 15:58:13 +08:00
Zexi Li 43d4c1e739 feat(monitor): add tag name/id mapping in metric measurement API (#25000)
Return structured MetricMeasurementOutput with TagNameIdMap and
TagNameIdValueMap so callers can resolve resource names to IDs.
2026-06-09 15:14:47 +08:00
cwz_eikoh bf8aab9f75 Feat/deployment hostpath (#24985)
* feat(llm): hostpath support in deployment

* fix(llm): status error in deployment & sku deleted by deployment accidentally
2026-06-08 11:23:34 +08:00
cwz_eikoh a8e5bf82eb feat(host): support host_path detected in scheduler (#24967) 2026-06-08 11:01:29 +08:00
屈轩 5cdadb69ce fix(region): avoid panic (#24988) 2026-06-08 10:58:47 +08:00
Zexi Li 9f35b4e597 fix(host): rewrite vm_name in telegraf influx proxy after rename (#24991)
Sync host guest desc on local VM rename and correct vm_name (and
tenant_id) tags when metadata service proxies agent metrics to TSDB.
2026-06-08 10:43:38 +08:00
Jian QiuandQiu Jian c80d865a24 fix: support ansible galaxy mirror (#24987)
Co-authored-by: Qiu Jian <qiujian@yunionyun.com>
2026-06-08 08:57:09 +08:00
屈轩 e0584f12e3 fix(region): support rockbasecloud (#24978) 2026-06-05 19:28:19 +08:00
屈轩 3ac9178c61 fix(monitor): skip disable account alert (#24979) 2026-06-05 16:14:25 +08:00
Jian QiuandQiu Jian 354408b656 fix: lbagent service code typo 20260604 (#24977)
Co-authored-by: Qiu Jian <qiujian@yunionyun.com>
2026-06-05 01:13:15 +08:00