v0.5.0

## 🚀  New Features Highlights
**Batch API & Multimodal and other OpenAI compatible API Surface**
- **Batch API Support**: Add OpenAI-style Batch API with simple LLM workers, Envoy/Gateway integration, JSONL & File List support, job pool sizing, and robust validation to safely offload large asynchronous workloads. (#1298, #1617, #1671, #1698, #1700, #1701)
- **Embeddings API and Moltimodal API**: Introduce OpenAI-compatible embeddings endpoint so online inference, search, and RAG traffic can share the same AIBrix control plane and routing. (#1570) Support multimodality deployments and for image/video generation for other engines. (#1678, #1679, #1603, #1584)
- **Files API & Unified Storage**: Implement OpenAI Files API plus a pluggable storage layer (local, S3, TOS, Redis metadata) to standardize artifact and batch job management across backends. (#1583, #1571)

**AIBrix KVCache Offloading frameworks & Connectors:**
- **High-Performance KVCache**: Adds GDR support, optimized collective communications, configurable max sequence length and batched tokens, multi-threading for higher concurrency, and block-hash based APIs plus external cache handles for flexible distributed deployments. (#1411, #1446, #1453, #1451, #1627, #1628, #1545, #1531, #1542)
- **Deep Engine Integrations**: Provide official AIBrix KVCache Dockerfiles and integration paths for vLLM and SGLang plus correctness fixes (head size, metrics, types) to make KV offloading a first-class option. (#1641, #1696, #1705, #1473, #1450, #1689)

**Production-Grade Prefill/Decode (P/D) Orchestration Support:**
- **New StormService Primitives**: Add PodSet API, PodGroup support, FullRecreate strategy, role upgrade sequences, roleStatuses, and richer RoleSet/PodSet fields to model multi-pod workers, shard groups, and safer rollout/rollback for complex topologies. (#1475, #1506, #1511, #1432, #1599, #1560)
- **P/D-Aware & Topology-Aware Routing**: Prefer P/D workers in the same RoleSet in replication mode, score candidates by locality/load, and harden PD routing behavior for Nixl-based setups. (#1409, #1634, #1429, #1601, #1703, #1693)
- **Role-Level Autoscaling for StormService**: Introduced the "subTargetSelector" field in the PodAutoscaler API, allowing independent autoscaling of specific roles (e.g., prefill, decode) within a StormService resource, particularly in pooled mode. (#1625)

## 📊 Feature Enhancements
- **Unified Runtime & Metadata**: Migrate metadata server from golang to Python for a simpler, lighter control path. Add liveness/readiness probes and shrink runtime image sizes. Improve downloader reliability and recursive object-store fetch support. (#1391, #1639, #1548, #1702, #1571)
- **LoRA & Model Adapter Reliability**: Support adapter scaling to desired replicas, refactor replica management, add wrappers, and enable LoRA downloading via the runtime to stabilize multi-adapter hosting.
 (#1132, #1472, #1670, #1680, #1537, #1541)
- **Autoscaling**: Unify and harden metrics fetching by adding retryable RestMetricsFetcher, shared client/aggregator and fixing race-condition for configuration updates  (#1466, #1487, #1620, #1621, #1709), Tune KPA defaults, support metric label selectors, and ensure PodAutoscaler emits events only when replica counts actually change. (#1624, #1629, #1630) scaling history decision has been supported in the status spec (#1618)
- **AIBrixRuntime Injection**: Deployment & StormService webhooks and wrapper libraries to auto-inject the runtime sidecar, standardizing metrics, downloads, and admin controls across engines.
 (#1403, #1457, #1543, #1681, #1561)

## 📦 Installation & Tooling & CI
- **Helm & Installation**: Strengthen the AIBrix Helm chart as the recommended deployment path by adding dedicated chart CI and fixes (#1370, #1424), enriching Chart.yaml metadata (#1414), introducing values.schema.json for input validation (#1415), supporting imagePullSecrets configuration (#1522), and resolving duplicate label issues for Flux Helm Controller compatibility (#1615). Made KubeRay optional for AIBrix installations if you do not use RayclusterFleet API(#1724)

## 🐞 Critical Bug Fixes
- Fixes StormService headless Service ownership and DNS behavior by setting proper ownerReferences and PublishNotReadyAddresses. (#1441, #1442)
- Fixes incorrect naming for AIBRIX_MODEL_GPU_PROFILE_CACHING_FLAG to ensure configuration consistency. (#1427)
- Fixes KVCache stability issues by preventing panic when watcher or metadata are not set in kvcache.spec. (#1526)
- Fixes PodAutoscaler and metrics correctness by emitting events only on replica changes, aggregating resources across all containers, handling optional MetricSource fields, validating multiple PodAutoscalers targeting the same workload, and ensuring PodSet autoscaler collects metrics from rank0. (#1630, #1643, #1648, #1662, #1704)

## New Contributors
- @JonathonShea made their first contribution in https://github.com/vllm-project/aibrix/pull/1427
- @bigerous made their first contribution in https://github.com/vllm-project/aibrix/pull/1442
- @jiangxiaobin96 made their first contribution in https://github.com/vllm-project/aibrix/pull/1431
- @mayooot made their first contribution in https://github.com/vllm-project/aibrix/pull/1496
- @zyfy29 made their first contribution in https://github.com/vllm-project/aibrix/pull/1505
- @zhengkezhou1 made their first contribution in https://github.com/vllm-project/aibrix/pull/1502
- @tianzhiqiang3 made their first contribution in https://github.com/vllm-project/aibrix/pull/1566
- @atakli made their first contribution in https://github.com/vllm-project/aibrix/pull/1574
- @jwjwjw3 made their first contribution in https://github.com/vllm-project/aibrix/pull/1573
- @lx1036 made their first contribution in https://github.com/vllm-project/aibrix/pull/1586
- @chethanuk made their first contribution in https://github.com/vllm-project/aibrix/pull/1558
- @baozixiaoxixi made their first contribution in https://github.com/vllm-project/aibrix/pull/1608
- @TylerGillson made their first contribution in https://github.com/vllm-project/aibrix/pull/1615
- @omrishiv made their first contribution in https://github.com/vllm-project/aibrix/pull/1626
- @lex1ng made their first contribution in https://github.com/vllm-project/aibrix/pull/1658
- @ChenTaoyu-SJTU made their first contribution in https://github.com/vllm-project/aibrix/pull/1672
- @zhenyu-02 made their first contribution in https://github.com/vllm-project/aibrix/pull/1682
- @yapple made their first contribution in https://github.com/vllm-project/aibrix/pull/1705
- @xvoron made their first contribution in https://github.com/vllm-project/aibrix/pull/1708
- @freedown19 made their first contribution in https://github.com/vllm-project/aibrix/pull/1716
- @Leafykn made their first contribution in https://github.com/vllm-project/aibrix/pull/1718

## What's Changed
**Full Changelog**: https://github.com/vllm-project/aibrix/compare/v0.4.0...v0.5.0

* Update installation guidance for v0.4.0 by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1406
* [Bug] fix webhook config output when using make manifests by @googs1025 in https://github.com/vllm-project/aibrix/pull/1412
* Feat: Add AIBrix Helm chart CI by @omerap12 in https://github.com/vllm-project/aibrix/pull/1370
* [Feature] KVCache: support GDR by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1411
* Select PD workers in same roleset by @varungup90 in https://github.com/vllm-project/aibrix/pull/1409
* [Bug] fix chart-ci by @omerap12 in https://github.com/vllm-project/aibrix/pull/1424
* [Misc]: Enhance Chart.yaml metadata with comprehensive information by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1414
* [feat]: Add values.schema.json for Helm chart input validation by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1415
* [Fix] Fix vLLM NIXL-based P/D samples by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1425
* [Bug] Corrected naming convention for AIBRIX_MODEL_GPU_PROFILE_CACHING_FLAG by @JonathonShea in https://github.com/vllm-project/aibrix/pull/1427
* Feat: add liveness & readiness probes to metadata service by @omerap12 in https://github.com/vllm-project/aibrix/pull/1391
* [Fix] Disable GGA in NIXL samples by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1436
* doc: correct release date in README.md by @nurali-techie in https://github.com/vllm-project/aibrix/pull/1435
* [Misc]: Remove v0.4.0 test files replaced by consolidated base templates by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1428
* feature: add stormservice webhook for inject aibrix runtime by @googs1025 in https://github.com/vllm-project/aibrix/pull/1403
* [Chore] KVCache: downgrade to cuda 12.1 by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1444
* [misc] Update vLLM PD disaggregation image by @happyandslow in https://github.com/vllm-project/aibrix/pull/1445
* [Misc] remove unuseless event by @googs1025 in https://github.com/vllm-project/aibrix/pull/1447
* [Feature] KVCache: support max seq len by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1446
* [Bug] stormservice's headless service not set ownerRef by @bigerous in https://github.com/vllm-project/aibrix/pull/1442
* [Bug] stormservice's headless service need set PublishNotReadyAddresses by @bigerous in https://github.com/vllm-project/aibrix/pull/1441
* [Bug] KVCache: fix metrics by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1450
* [Improvement] KVCache: optimize coll communication by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1451
* Fix P/D disaggregation router to follow Nixl kv_transfer_params by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1429
* [Misc] fix regression test manifests by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1456
* [Bug] KVCache: fix max seq len support by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1453
* fix: align envoy pod template labels with controller selector by @omerap12 in https://github.com/vllm-project/aibrix/pull/1439
* [Docs] Update helm installation guidance by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1461
* Refactor to use single loop for least request pod selection by @jiangxiaobin96 in https://github.com/vllm-project/aibrix/pull/1431
* [Misc]: Updates docs to reflect the latest router interface by @googs1025 in https://github.com/vllm-project/aibrix/pull/1465
* [Misc] Add development workload samples by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1467
* Feat(autoscaler): Add retry delays to RestMetricsFetcher by @omerap12 in https://github.com/vllm-project/aibrix/pull/1466
* [Feat] Support adapter scaling to desired replicas by @dittops in https://github.com/vllm-project/aibrix/pull/1132
* [fix] Correct the headless service ownerReference UID in tests by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1469
* Refactor: Extract KV event management to break circular dependency by @ae86zhizhi in https://github.com/vllm-project/aibrix/pull/1401
* [Integration] correct head size calculation for AIBrix connectors by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1473
* Cut release v0.4.1 by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1477
* Update installation guidance for v0.4.1 by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1479
* add least_request_test by @jiangxiaobin96 in https://github.com/vllm-project/aibrix/pull/1463
* [Test]: add controller integration test framework by @googs1025 in https://github.com/vllm-project/aibrix/pull/1448
* Fix missing traffic_pattern parameters in benchmark script by @happyandslow in https://github.com/vllm-project/aibrix/pull/1484
* [Misc] Enhance S3Downloader error handling and IRSA support by @ronaldosaheki in https://github.com/vllm-project/aibrix/pull/1483
* [Chore] KVCache: update torch version by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1490
* refactor(scheme): prevent duplicate registration in RegisterSchemas by @googs1025 in https://github.com/vllm-project/aibrix/pull/1464
* [DOCS] fix: add ReferenceGrant configuration by @omerap12 in https://github.com/vllm-project/aibrix/pull/1486
* Feat: Support role upgrade sequences in stormservice by @omerap12 in https://github.com/vllm-project/aibrix/pull/1432
* [Feat]: add deployment webhook to inject AIBrixRuntime sidecar container by @googs1025 in https://github.com/vllm-project/aibrix/pull/1457
* refactor: improve autoscaler metrics fetcher design by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1487
* [feat]: Add PodSet API for multi-pod worker support in StormService by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1475
* Fix missing FQDN and reuse hash func from syncer by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1500
* [fix] deep copy template to avoid hash mutation issue by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1501
* [Docs] Add `Using NodePort to Expose the Gateway API` section by @mayooot in https://github.com/vllm-project/aibrix/pull/1496
* [Misc] Add unit tests for least_busy_time by @omerap12 in https://github.com/vllm-project/aibrix/pull/1495
* add rolset integration test by @googs1025 in https://github.com/vllm-project/aibrix/pull/1491
* [Misc]: ignore AlreadyExists and NotFound in controller operations by @googs1025 in https://github.com/vllm-project/aibrix/pull/1507
* [Misc] Add unit test for least util routing algorithm by @jiangxiaobin96 in https://github.com/vllm-project/aibrix/pull/1497
* [Misc] test: add unit test for leastGpuCacheRouter by @zyfy29 in https://github.com/vllm-project/aibrix/pull/1505
* [Bug] fix count ready podset condition by @Epsilon314 in https://github.com/vllm-project/aibrix/pull/1518
* [Misc]: add sync-crds makefile cmd by @googs1025 in https://github.com/vllm-project/aibrix/pull/1513
* [Misc] Refactor KPA algorithm by @omerap12 in https://github.com/vllm-project/aibrix/pull/1503
* [CI]: add verify_crd makefile by @googs1025 in https://github.com/vllm-project/aibrix/pull/1514
* [Misc]chore: ignore auto-generated ` _version.py` file by @zhengkezhou1 in https://github.com/vllm-project/aibrix/pull/1502
* [Feat] Improve ModelAdapter reliability with retry and pod switching by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1472
* [Misc] Fix incorrect expressions for mean TTFT and TPOP in Grafana by @rudeigerc in https://github.com/vllm-project/aibrix/pull/1521
* [Docs] Add development test guidance by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1520
* [feat]Add imagePullSecrets values for helm by @my-git9 in https://github.com/vllm-project/aibrix/pull/1522
* [Misc] Add autoscaling validation of minReplicas and maxReplicas by @jiangxiaobin96 in https://github.com/vllm-project/aibrix/pull/1508
* [Misc] test: add unit test for throughputRouter by @zyfy29 in https://github.com/vllm-project/aibrix/pull/1516
* [Misc] test: add unit test for leastKvCacheRouter by @zyfy29 in https://github.com/vllm-project/aibrix/pull/1515
* [MISC]: add test for least_load by @omerap12 in https://github.com/vllm-project/aibrix/pull/1524
* [Bug]fix panic when watcher and metadata not set in kvcache.spec by @zhixian82 in https://github.com/vllm-project/aibrix/pull/1526
* [Bug]: fix annotation in deployment webhook by @googs1025 in https://github.com/vllm-project/aibrix/pull/1527
* [Misc] Generate StormService golang client by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1532
* [Feature] KVCache: support external cache handle by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1531
* [Misc] add model adapter wrapper by @nurali-techie in https://github.com/vllm-project/aibrix/pull/1537
* [Misc]: add podset integration test by @googs1025 in https://github.com/vllm-project/aibrix/pull/1533
* [Bug] use fallback value to prevent divide zero error by @zyfy29 in https://github.com/vllm-project/aibrix/pull/1517
* [Refactor] KVCache: simplify external cache handle create API by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1542
* [MISC] Add wrapper for stormservice by @omerap12 in https://github.com/vllm-project/aibrix/pull/1543
* [Misc] add kvcache wrapper by @nurali-techie in https://github.com/vllm-project/aibrix/pull/1541
* [Misc]: add stormservice integration test by @googs1025 in https://github.com/vllm-project/aibrix/pull/1544
* Improve the runtime downloader quality by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1548
* [misc] Consolidate tests under top-level python tests by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1549
* [runtime] Improve lora registration reliability by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1550
* [runtime] Enrich engine metrics and add support for sglang by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1551
* Improve upgradeOrder behavior more intuitive and safer  by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1547
* [CI] fix vllm-mock runtime sidecar startup issue by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1555
* [Mics]: exclude integration tests from make test by @googs1025 in https://github.com/vllm-project/aibrix/pull/1556
* [Misc] test: modify apa scale test by @jiangxiaobin96 in https://github.com/vllm-project/aibrix/pull/1523
* [Misc] add deployment wrapper by @nurali-techie in https://github.com/vllm-project/aibrix/pull/1561
* [API] KVCache: support block hashes by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1545
* [API] Add "FullRecreate" strategy for atomic PodSet recovery by @mayooot in https://github.com/vllm-project/aibrix/pull/1511
* [Misc]: add more field for stormservice roleset podset by @googs1025 in https://github.com/vllm-project/aibrix/pull/1560
* [Misc] (test): add unit test for prefix_cache_preble by @zhengkezhou1 in https://github.com/vllm-project/aibrix/pull/1519
* [MISC] Refactor labels.go & add unit tests by @omerap12 in https://github.com/vllm-project/aibrix/pull/1563
* fix(deploy): add missing labels to pod template by @googs1025 in https://github.com/vllm-project/aibrix/pull/1568
* [Docs]: update installation guide for AIBrix with Helm prerequisites … by @haitwang-cloud in https://github.com/vllm-project/aibrix/pull/1539
* Add multi-metrics-source-support for hpa by @tianzhiqiang3 in https://github.com/vllm-project/aibrix/pull/1566
* Update the broken link related to vllm metrics by @atakli in https://github.com/vllm-project/aibrix/pull/1574
* [feat]Add tolerations values for chart by @my-git9 in https://github.com/vllm-project/aibrix/pull/1579
* [Feat] Batch API Service, working with temporary existing local batch driver by @zhangjyr in https://github.com/vllm-project/aibrix/pull/1298
* [Bug] fix: unexpectedly high TTFT in benchmarks results of reasoning (Chain-of-Thought) LLMs by @jwjwjw3 in https://github.com/vllm-project/aibrix/pull/1573
* [Misc] Suppress info logs in integration tests by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1585
* [Bug] add the return value check to pass linter by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1588
* [Feat] Enable redis password in helm chart by @lx1036 in https://github.com/vllm-project/aibrix/pull/1586
* [Misc] Add tests for FallbackRouter by @chethanuk in https://github.com/vllm-project/aibrix/pull/1558
* [CI] Exclude integration tests from race condition test by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1590
* [feat] Add embedding API by @varungup90 in https://github.com/vllm-project/aibrix/pull/1570
* [Mics]: optimize deleteReferenceGrant with label selector in ModelRouter controller by @googs1025 in https://github.com/vllm-project/aibrix/pull/1589
* refactor: implement clean layered autoscaler architecture by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1575
* [Misc] Remove type and impl duplication in autocaler by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1596
* [Feat] Support OpenAI Files API and refactor storage library to support local, s3, tos, and redis (for metadata) by @zhangjyr in https://github.com/vllm-project/aibrix/pull/1583
* Add recursive download for tos v2/s3 client by @happyandslow in https://github.com/vllm-project/aibrix/pull/1571
* [API]: add roleStatuses field in stormservice api by @googs1025 in https://github.com/vllm-project/aibrix/pull/1599
* Add gateway-plugin support to generate image and video by @varungup90 in https://github.com/vllm-project/aibrix/pull/1603
* Improve pdRouter with load-aware routing by @googs1025 in https://github.com/vllm-project/aibrix/pull/1601
* [Misc]: add more field for podautoscaler resource by @omerap12 in https://github.com/vllm-project/aibrix/pull/1611
* [Docs]: Update set_metrics override keys and example curl by @googs1025 in https://github.com/vllm-project/aibrix/pull/1612
* Use EnqueueRequestsFromMapFunc for KVCache controller by @baozixiaoxixi in https://github.com/vllm-project/aibrix/pull/1608
* [Misc] Add tests for PrefixCacheRouting by @chethanuk in https://github.com/vllm-project/aibrix/pull/1587
* Simplify autoscaler by unifying client and aggregator by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1620
* Resolve the UpdateConfiguration race issue in autoscaler by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1621
* Bug: remove duplicate labels that prevent flux helm-controller from deploying the aibrix chart by @TylerGillson in https://github.com/vllm-project/aibrix/pull/1615
* Support scaling behaviors and remove configuration duplication by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1622
* [Docs] update aws documentation to include AI on EKS AIBrix deployment by @omrishiv in https://github.com/vllm-project/aibrix/pull/1626
* feat: add scaling history decision in the status spec by @omerap12 in https://github.com/vllm-project/aibrix/pull/1618
* [Chore] KVCache: add max_num_batched_tokens config by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1627
* feat: support metric label by @baozixiaoxixi in https://github.com/vllm-project/aibrix/pull/1624
* [Misc] Benchmark: add duration limit and max concurrent sessions settings to client by @ronaldosaheki in https://github.com/vllm-project/aibrix/pull/1632
* Support P/D Pooling autoscaling in StormService by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1625
* [Feat] OpenAI Batch API Support with Simple LLM Workers by @zhangjyr in https://github.com/vllm-project/aibrix/pull/1617
* [Bug] podautoscaler: only emit when replica count changes by @omerap12 in https://github.com/vllm-project/aibrix/pull/1630
* update stable and panic value for KPA by @baozixiaoxixi in https://github.com/vllm-project/aibrix/pull/1629
* [Mics]: support qos and burst flag in controller by @googs1025 in https://github.com/vllm-project/aibrix/pull/1637
* feat(metrics): add autoscaler scale action prometheus metric by @omerap12 in https://github.com/vllm-project/aibrix/pull/1638
* [Misc]: sync crds file to helm by @googs1025 in https://github.com/vllm-project/aibrix/pull/1635
* [Feature] KVCache: support multi-threading mode by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1628
* [Integration] vllm aibrix scheduler and connectors by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1641
* [Feat] Migrate metadata server from Go to Python by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1639
* [Doc] Refining workload generator documentation by @happyandslow in https://github.com/vllm-project/aibrix/pull/1631
* [Misc] Multimodality Scenarios Sample Deployment by @happyandslow in https://github.com/vllm-project/aibrix/pull/1584
* [Bug] fix: aggregate resource metrics across all containers in pod by @googs1025 in https://github.com/vllm-project/aibrix/pull/1643
* [Bug]: Make optional fields in MetricSource by @googs1025 in https://github.com/vllm-project/aibrix/pull/1648
* Add requirements file and fix api-key bug by @omerap12 in https://github.com/vllm-project/aibrix/pull/1657
* [Doc] Support batch inference usage doc by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1646
* [Bug]: add validation for multiple PodAutoscalers targeting the same workload by @googs1025 in https://github.com/vllm-project/aibrix/pull/1662
* [Misc] refactor roleSet test validation to use validation Package by @lex1ng in https://github.com/vllm-project/aibrix/pull/1658
* [Misc] add num_waiting_reqs metrics by @scarlet25151 in https://github.com/vllm-project/aibrix/pull/1668
* [Mics]: fix retry reconciler in podautoscaler controller by @googs1025 in https://github.com/vllm-project/aibrix/pull/1669
* [Misc] Batch API envoy integration fix, E2E verification, and document update by @zhangjyr in https://github.com/vllm-project/aibrix/pull/1671
* [Misc] Added unit test for WorkloadScale by @nurali-techie in https://github.com/vllm-project/aibrix/pull/1666
* [Misc] Added unit test for APA post autoscaler by @nurali-techie in https://github.com/vllm-project/aibrix/pull/1659
* [MISC] add unit test for podautoscaler monitor by @omerap12 in https://github.com/vllm-project/aibrix/pull/1676
* [CLI] Fix replicate args assignment in main.go by @ChenTaoyu-SJTU in https://github.com/vllm-project/aibrix/pull/1672
* Link to system-installed zmq without building by @autopear in https://github.com/vllm-project/aibrix/pull/1372
* Refactor the model adapter replicas feature by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1670
* Add e2e OpenAI API compatibility test by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1678
* Make Gateway API compatible with OpenAI API by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1679
* Support downloading lora models through runtime by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1680
* [Misc] Optimize runtime sidecar injection logic by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1681
* [Docs] Add VKE docs and update P/D examples on VKE by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1687
* [Misc] Add Integration Test Utilities for PodAutoscaler Controller by @zhenyu-02 in https://github.com/vllm-project/aibrix/pull/1682
* [Fix] KVCache: fix result type of group aware kv manager by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1689
* [Feat]: support mulit metrics for podautoscaler by @googs1025 in https://github.com/vllm-project/aibrix/pull/1688
* [Feat]: add podautoscaler webhook by @googs1025 in https://github.com/vllm-project/aibrix/pull/1683
* [Misc] Added unit tests for WorkloadScale.SetDesiredReplicas by @nurali-techie in https://github.com/vllm-project/aibrix/pull/1692
* [Bug]: fix pd route Algorithms do not check http route by @googs1025 in https://github.com/vllm-project/aibrix/pull/1693
* [Integration] Update vLLM v0.10.2 patch by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1695
* [Integration] add AIBrix KVCache x vLLM dockerfile by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1696
* [batch] Bug fixes and code Improvements in batch API by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1698
* [batch] Support File List API, configurable job pool size and error file handling by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1700
* [batch] Add jsonl input and file validation by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1701
* [CI] Reduce runtime container image size by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1702
* [Misc] Improve P/D router reliability by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1703
* [Misc] Added unit tests related to PodAutoscaler by @nurali-techie in https://github.com/vllm-project/aibrix/pull/1694
* [Integration] clone repo w/ tags in vLLM dockerfile by @DwyaneShi in https://github.com/vllm-project/aibrix/pull/1706
* [Integration] add AIBrix KVCache x SGLang dockerfile by @yapple in https://github.com/vllm-project/aibrix/pull/1705
* [BUG] fix: aibrix_benchmark streaming issue #1674 by @xvoron in https://github.com/vllm-project/aibrix/pull/1708
* [Misc]Add unit tests related to gateway server by @freedown19 in https://github.com/vllm-project/aibrix/pull/1716
* [Docs]: add multi metrics podautoscaler docs by @googs1025 in https://github.com/vllm-project/aibrix/pull/1712
* [feat]: Select and score P/D in same roleset by @varungup90 in https://github.com/vllm-project/aibrix/pull/1634
* fix: autoscaler for the podset only collect metrics from rank0 by @scarlet25151 in https://github.com/vllm-project/aibrix/pull/1704
* [Misc] Added unit test for metrics fetcher by @nurali-techie in https://github.com/vllm-project/aibrix/pull/1709
* [Misc] Made KubeRay optional for AIBrix installations by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1724
* [fix] Moved deps from profiling group back to main by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1726
* [Docs] Add volcano engine startup docs and quick start by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1725
* feat: add EIC connector by @Leafykn in https://github.com/vllm-project/aibrix/pull/1718
* [API] stormservice support podgroup by @Epsilon314 in https://github.com/vllm-project/aibrix/pull/1506
* Cut v0.5.0 release by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1737
* [Docs] Improve the docs and examples by @Jeffwan in https://github.com/vllm-project/aibrix/pull/1738

## New Contributors
* @JonathonShea made their first contribution in https://github.com/vllm-project/aibrix/pull/1427
* @bigerous made their first contribution in https://github.com/vllm-project/aibrix/pull/1442
* @jiangxiaobin96 made their first contribution in https://github.com/vllm-project/aibrix/pull/1431
* @mayooot made their first contribution in https://github.com/vllm-project/aibrix/pull/1496
* @zyfy29 made their first contribution in https://github.com/vllm-project/aibrix/pull/1505
* @zhengkezhou1 made their first contribution in https://github.com/vllm-project/aibrix/pull/1502
* @tianzhiqiang3 made their first contribution in https://github.com/vllm-project/aibrix/pull/1566
* @atakli made their first contribution in https://github.com/vllm-project/aibrix/pull/1574
* @jwjwjw3 made their first contribution in https://github.com/vllm-project/aibrix/pull/1573
* @lx1036 made their first contribution in https://github.com/vllm-project/aibrix/pull/1586
* @chethanuk made their first contribution in https://github.com/vllm-project/aibrix/pull/1558
* @baozixiaoxixi made their first contribution in https://github.com/vllm-project/aibrix/pull/1608
* @TylerGillson made their first contribution in https://github.com/vllm-project/aibrix/pull/1615
* @omrishiv made their first contribution in https://github.com/vllm-project/aibrix/pull/1626
* @lex1ng made their first contribution in https://github.com/vllm-project/aibrix/pull/1658
* @ChenTaoyu-SJTU made their first contribution in https://github.com/vllm-project/aibrix/pull/1672
* @zhenyu-02 made their first contribution in https://github.com/vllm-project/aibrix/pull/1682
* @yapple made their first contribution in https://github.com/vllm-project/aibrix/pull/1705
* @xvoron made their first contribution in https://github.com/vllm-project/aibrix/pull/1708
* @freedown19 made their first contribution in https://github.com/vllm-project/aibrix/pull/1716
* @Leafykn made their first contribution in https://github.com/vllm-project/aibrix/pull/1718

**Full Changelog**: https://github.com/vllm-project/aibrix/compare/v0.4.0...v0.5.0