vllm-stack-0.1.1

The stack deployment of vLLM

What's Changed

• [CI/Build][Router] Make semantic caching optional by @Shaoting-Feng in #218
• [Benchmark] Add router config in tutorial by @Shaoting-Feng in #223
• refactor: standard fastapi project structure for better main… by @BrianPark314 in #217
• Added lora support proposal by @wangchen615 in #216
• [Feat] Added initContainer to modelSpec by @AbelHristodor in #221
• [Router] Fix semantic cache check in chat completion url by @Shaoting-Feng in #224
• [Doc] Change repo in tutorial 08 naive k8s by @Shaoting-Feng in #225
• [Doc] Update community meeting calendar invite by @YuhanLiu11 in #231
• [Doc] Fix startupProbe indentation in values-07 tutorial file by @AbelHristodor in #226
• [Doc] Initial docs structure by @Siddhant-Ray in #234
• [Doc] Update endpoint in 01 tutorial by @Shaoting-Feng in #236
• [Doc] add example page and readme by @Siddhant-Ray in #241
• [Doc] Fix typo of model name and output len in AIBrix by @Shaoting-Feng in #242
• [Doc] Add doc page for benchmark qa by @Siddhant-Ray in #243
• [Doc] add doc on gcp.rst by @EaminC in #249
• [Feat] add vllm-api-key by @JustinDuy in #194
• [CI/Build] Add concurrency to functionality test by @Shaoting-Feng in #219
• [Doc] update tutorial and user manual docs by @Siddhant-Ray in #257
• [Doc] Add docs for router CRD config and dev, some small tweaks by @Siddhant-Ray in #259
• [FEAT] Terraform Quickstart Tutorials for Google GKE by @falconlee236 in #250
• [Feat] add requestGPUType to modelSpec by @Hexoplon in #253
• [Doc][CI/Build] Minor fix by @Shaoting-Feng in #258
• [Doc] dev api docs, bug fixes by @Siddhant-Ray in #266
• [Feat] add explicit resource limit values by @Hexoplon in #255
• [DOC] format unified gcp.rst adding trouble shooting by @EaminC in #263
• [Doc] Minor fix in tutorial by @YuhanLiu11 in #272
• [Doc] Minor fix in benchmarking scripts by @YuhanLiu11 in #273
• [Tutorial] Deployment on Azure AKS by @surajssd in #247
• [Feat] add model label on engine deployments by @Hexoplon in #269
• [Misc] Add schedulerName in servingEngineSpec by @hongkunyoo in #275
• [Feat] Remove sudo requirement for kubectl and helm by @Romero027 in #256
• [Benchmark] Minor fix in benchmark script by @YuhanLiu11 in #284
• [Benchmark] Minor updates to benchmark script by @YuhanLiu11 in #286
• [Doc] Minor fix in tutorials by @YuhanLiu11 in #288
• [Feat] add extraVolume and extraVolumeMount helm variables by @Hexoplon in #280
• Update 09-lora-enabled-installation.md by @wangchen615 in #287
• chore: use extra deps to optionally install additional pkg by @rootfs in #289
• [Feat] Request rewriter interface in router by @ApostaC in #230
• [Feat] add security context to servingEngineSpec by @Hexoplon in #282
• [Doc] add docs link to readme by @Siddhant-Ray in #290
• chore: update e2e test to use python 3.12 to match setup.py requirements by @rootfs in #295
• [CI/Build] Github action for building docs pipeline by @Siddhant-Ray in #291
• Add .readthedocs.yaml by @hmellor in #296
• Hotfix readthedocs build by @hmellor in #298
• Update docs link in README by @hmellor in #299
• feat: support PII detection in http request by @rootfs in #235
• [Bugfix]: add missing v1 prefix by @Xunzhuo in #302
• [Misc] Bumping version to 0.1.1 by @YuhanLiu11 in #308

New Contributors

• @AbelHristodor made their first contribution in #221
• @JustinDuy made their first contribution in #194
• @falconlee236 made their first contribution in #250
• @Hexoplon made their first contribution in #253
• @surajssd made their first contribution in #247
• @hongkunyoo made their first contribution in #275
• @Romero027 made their first contribution in #256
• @Xunzhuo made their first contribution in #302

Full Changelog: vllm-stack-0.1.0...vllm-stack-0.1.1