opensource/cloudpods
3
0
Fork 0
mirror of https://github.com/yunionio/cloudpods.git synced 2026-09-19 10:46:58 +08:00
Code Issues Packages Projects Releases Wiki Activity
20,906 Commits 27 Branches 687 Tags
f538dcf2e606397bc2ba5d9245d2c2cf97772213
Commit Graph
16398 Commits
Author SHA1 Message Date
Zexi Li f538dcf2e6 feat(aiproxy): add Anthropic Messages API and migrate functional tests to Go (#25097) 
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 20:13:03 +08:00
屈轩 8c87c0e57d fix(region): pve host driver compatibility (#25099) 2026-07-03 15:37:58 +08:00
Zexi Li c91b5bc70c feat(llm): add ModelScope instant model import and refactor model download (#25091) 
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 20:12:59 +08:00
Zexi Li f1f3c1df2a feat(llm): support local_path scheduling with prefer_hosts and deployment restart (#25085) 2026-07-01 13:11:02 +08:00
wanyaoqi f6e5f71fba fix(host-deployer): mount procfs before deploy guestfs (#25086) 2026-07-01 00:53:31 +08:00
Zexi Li 00bcdae23f feat(scheduler): append GPU reserved resource hints on predicate failure (#25083) 2026-06-30 15:40:34 +08:00
Zexi Li 3413845e96 feat(llm): backfill orphan LLM instances into deployments on init (#25079) 
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 11:26:16 +08:00
wanyaoqi b47a802515 fix(host-deployer): do base64 windows password (#25070) 2026-06-27 06:48:35 +08:00
屈轩 90ea5b77b0 fix(region): quota check (#25076) 2026-06-26 13:05:30 +08:00
wanyaoqi 372fae41c6 fix(region,host): kvm guest change disk driver reset uefi vars (#25068) 2026-06-26 10:20:25 +08:00
wanyaoqi 3b796dc0e8 fix(host): qemu set multifd before start incoming migration (#25064) 
use drive mirror do block migration
 2026-06-26 10:18:45 +08:00
Zexi Liandcwz d3b4ab273a Automated cherry pick of #25074: feat(llm): tool call defaults & auto gpu ultilization (#25075) 
* feat(llm): upgrade auto-gpu-ultilization

* feat(llm): add vllm tool call defaults

* feat(llm): add sglang tool call defaults

---------

Co-authored-by: cwz <cwz_eikoh@163.com>
 2026-06-26 10:15:55 +08:00
Zexi Li 686b0f3872 feat(llm): async instant model delete and improve import status tracking (#25072) 
fix(aiproxy): set OpenAI handler process timeouts and skip upstream error
response when request context is already cancelled.
 2026-06-25 19:52:28 +08:00
Zexi Li b52aa5de85 feat(llm): validate GPU devices on deployment create and improve error messages (#25062) 2026-06-24 14:26:18 +08:00
wanyaoqi 043eac88ba fix(region): snapshot validate add check guest is quorum master guest (#25052) 2026-06-24 10:30:14 +08:00
cwz_eikoh c3db76457d Automated cherry pick of #25016: Feature/http get+llm probe (#25045) 
* hostman: probe http get in pod netns

* llm: watch pod status for service readiness
 2026-06-23 19:40:46 +08:00
屈轩 854b93e3a4 fix(region): filter sku by zone ids (#25061) 2026-06-23 15:14:51 +08:00
Zexi Li 5a4bbefe72 fix(aiproxy): defer stream context cancel until chunks are consumed (#25058) 2026-06-23 14:09:37 +08:00
Zexi Li 4237ce52ea feat(llm): sync llm deployment with aiproxy catalog and routing (#25013) 
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 19:35:50 +08:00
cwz_eikoh d2bbda642b Automated cherry pick of #25044: Feature/llm route for aiproxy (#25046) 
* feat(aiproxy): support routing model in aiproxy

* feat(llm): add llm-router
 2026-06-22 10:09:58 +08:00
Jian QiuandQiu Jian c6225bc046 fix: credential scope revisit (#25050) 
Co-authored-by: Qiu Jian <qiujian@yunionyun.com>
 2026-06-21 09:25:58 +08:00
wanyaoqi c559974e44 fix(host): recycle servers dir on guest delete (#25022) 2026-06-21 08:34:26 +08:00
Jian QiuandQiu Jian 5392cfc8a9 fix: some host_type should consider container (#25048) 
Co-authored-by: Qiu Jian <qiujian@yunionyun.com>
 2026-06-20 09:47:47 +08:00
屈轩 9f0d1af484 fix(region): remove debug log (#25042) 2026-06-17 14:50:25 +08:00
屈轩 0956e660a4 fix(region): aws dedicated host sync (#25040) 2026-06-16 20:14:27 +08:00
屈轩andCursor 4bce487605 fix(compute): polish httperrors error messages in pkg/compute (#25036) 
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 20:49:22 +08:00
Zexi Li 81ebea9451 feat(llm): add community images catalog API (#25030) 
Expose llmimages.yaml as list/show/refresh endpoints with configurable
source URL, periodic cache refresh, and mcclient module support.
 2026-06-15 17:26:25 +08:00
屈轩 acac258359 fix(region): filter sku by zone ids (#25029) 2026-06-15 15:50:46 +08:00
屈轩 c0f9765f9c fix(region): vendor update (#25027) 2026-06-15 14:58:14 +08:00
屈轩 fadd9b92f2 fix(region): struct tag fix (#25024) 2026-06-15 13:57:10 +08:00
wanyaoqi a3a14bbed7 fix(region): guest detach isolated devices add is_force options (#25020) 2026-06-15 09:54:40 +08:00
屈轩 fc795b15c0 fix(region): disk througput sync (#25018) 2026-06-13 11:56:18 +08:00
wanyaoqi 8527232b7c fix(host): guest python launcher error (#25012) 2026-06-12 14:02:36 +08:00
屈轩 ded845a3dc fix(region): optimized sku query (#25009) 2026-06-11 14:31:29 +08:00
wanyaoqi 3172a1e86c fix(region): host model add api stats (#24955) 2026-06-09 23:01:40 +08:00
屈轩 7cff45fb5b feat(aiproxy): add aiproxy (#25003) 2026-06-09 18:54:54 +08:00
屈轩 5a2bfd9b5a fix(region): sku price (#25002) 2026-06-09 15:58:18 +08:00
Zexi Li 9f1e77deb6 feat(monitor): add tag name/id mapping in metric measurement API (#24999) 
Return structured MetricMeasurementOutput with TagNameIdMap and
TagNameIdValueMap so callers can resolve resource names to IDs.
 2026-06-09 15:14:35 +08:00
Zexi Liandcwz 72d7bd23b4 Automated cherry pick of #24985: Feat/deployment hostpath (#24993) 
* feat(llm): hostpath support in deployment

* fix(llm): status error in deployment & sku deleted by deployment accidentally

---------

Co-authored-by: cwz <cwz_eikoh@163.com>
 2026-06-08 11:23:48 +08:00
Zexi Liandcwz 51a85f66ba feat(host): support host_path detected in scheduler (#24992) 
Co-authored-by: cwz <cwz_eikoh@163.com>
 2026-06-08 11:01:14 +08:00
屈轩 035e31d9bf fix(region): avoid panic (#24989) 2026-06-08 10:58:27 +08:00
Zexi Li 3d086abf3e fix(host): rewrite vm_name in telegraf influx proxy after rename (#24983) 
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 10:43:18 +08:00
Jian QiuandQiu Jian d9419958d7 fix: support ansible galaxy mirror (#24986) 
Co-authored-by: Qiu Jian <qiujian@yunionyun.com>
 2026-06-08 08:56:48 +08:00
屈轩 cfb9a97c78 fix(region): support rockbasecloud (#24984) 2026-06-05 19:28:48 +08:00
屈轩 957e785bd3 fix(monitor): skip disable account alert (#24980) 2026-06-05 16:14:28 +08:00
Jian QiuandQiu Jian f082dc9b2d fix: lbagent service code typo 20260604 (#24976) 
Co-authored-by: Qiu Jian <qiujian@yunionyun.com>
 2026-06-05 01:13:36 +08:00
屈轩 f2d7af548e fix(region): prefer zones (#24972) 2026-06-04 18:52:01 +08:00
Zexi Li e42070a852 fix(llm): 更新 model catalog 默认 URL 与 webtop 镜像同步 (#24973) 
将 ModelCatalogURL 默认路径改为 model-catalog.yaml；
sync_llm_images 改为同步 fedora-xfce webtop 并注释其它候选镜像。
 2026-06-04 18:51:12 +08:00
Zexi Li a1ba61b875 fix(llm): container desktop (#24970) 2026-06-04 11:51:41 +08:00
Zexi Li 80dcd3ae42 fix(monitor): alert_state of resource metrics api (#24964) 2026-06-03 17:15:31 +08:00