vllm-stack-0.0.8

The stack deployment of vLLM

What's Changed

• Fix the problem of 1k prompts. by @ggaaooppeenngg in #127
• [Router] Fix unspecified versions in requirements.txt by @Shaoting-Feng in #143
• [CI/Build] Fix static router in github actions by @Shaoting-Feng in #137

Full Changelog: vllm-stack-0.0.7...vllm-stack-0.0.8

vllm-stack-0.0.7

The stack deployment of vLLM

What's Changed

• [Tutorial] Added EKS tutorial for production stack by @Hanchenli in #142
• [Deploy WIP] Modified the EKS tutorial by @Hanchenli in #144

Full Changelog: vllm-stack-0.0.6...vllm-stack-0.0.7

vllm-stack-0.0.6

The stack deployment of vLLM

What's Changed

• [CI/Build] Remove useless steps by @Shaoting-Feng in #124
• [Doc] Fix grafana graph by @Shaoting-Feng in #128
• Bugfix: configurable deployment options by @BrianPark314 in #121
• [Router] Support Batch API part 2 by @gaocegege in #109
• [Doc] minor tutorial doc fix by @vMaroon in #138
• [Doc] fixed chart-name related misalignments in tutorial docs by @vMaroon in #139
• [Doc] Add code of conduct by @Siddhant-Ray in #130
• [Doc] Running vLLM with tensor parallelism by @YuhanLiu11 in #140
• Added StorageClass in PVC template by @Hanchenli in #141

New Contributors

• @vMaroon made their first contribution in #138
• @Siddhant-Ray made their first contribution in #130

Full Changelog: vllm-stack-0.0.5...vllm-stack-0.0.6

vllm-stack-0.0.5

What's Changed

• [Bugfix] value file based accessMode by @BrianPark314 in #108
• [Doc] Correct router path in the README by @ggaaooppeenngg in #113
• [Router] Add 'v1' prefix in the OpenAI API by @ggaaooppeenngg in #117
• [Doc] Adding contributing guidelines by @Shaoting-Feng in #120
• [Feat] Enable static service discovery on router through Helm by @0xThresh in #111
• feat: adjustable deployment strategy by @BrianPark314 in #118

New Contributors

• @ggaaooppeenngg made their first contribution in #113

Full Changelog: vllm-stack-0.0.4...vllm-stack-0.0.5

vllm-stack-0.0.4

What's Changed

• [Doc] Update README.md by @Shaoting-Feng in #73
• feat: OpenAI batch API part 1 by @gaocegege in #52
• [Add] fix for router files api and example to post query to the api by @ApostaC in #76
• feat: Add basic issue templates by @gaocegege in #79
• chore: Add test cases for file storage by @gaocegege in #82
• feat: Wrap router to a singleton by @gaocegege in #83
• adding step-by-step tutorial links in readme by @junchenj in #84
• [Doc] Fix README section by @Shaoting-Feng in #85
• chore: Refine README, adjust image size by @gaocegege in #88
• [Doc] Add PR template by @Shaoting-Feng in #93
• feat(router): generate req id with uuid. by @Electronic-Waste in #89
• Feat: Add support for disabling router by @0xThresh in #96
• Update yaml file for the tutorials by @junchenj in #98
• [CI/Build] : add GitHub Actions workflows for router (#74) by @Sozhan308 in #94
• [CI/Build] Add helm update to helm func test pipeline by @Shaoting-Feng in #99
• [CI/Build] Avoid using helm repo by @Shaoting-Feng in #100
• Enable multi-GPU inference in vLLM with tensor parallelism by @YuhanLiu11 in #105

New Contributors

• @junchenj made their first contribution in #84
• @Electronic-Waste made their first contribution in #89
• @Sozhan308 made their first contribution in #94
• @YuhanLiu11 made their first contribution in #105

Full Changelog: vllm-stack-0.0.3...vllm-stack-0.0.4

vllm-stack-0.0.3

What's Changed

• chore: Unit test in github action by @gaocegege in #24
• feat: Update README to use new vLLM chart hosting URL by @0xThresh in #25
• Update 01-minimal-helm-installation.md by @Shaoting-Feng in #27
• [Doc] Fix Readme for 01 example by @Shaoting-Feng in #32
• fix: Fix docs about router by @gaocegege in #33
• Documentation fixes by @dmatch01 in #29
• Add pre-commit based linting and formatting by @hmellor in #35
• [CI/CD] Functionality test for helm chart by @Shaoting-Feng in #30
• feat: add configurable resource values to router deployment by @0xThresh in #38
• Fix helm chart issue by @dxu104 in #42
• [fix] triggers for functionality test by @ApostaC in #46
• chore: Use choices in CLI by @gaocegege in #48
• feat: Make log stats interval as a hidden CLI argument by @gaocegege in #49
• Polish the 'Setting Up a Kubernetes Environment with GPUs' tutorial by @waltforme in #51
• [CI/Build] Upgrade function test by @Shaoting-Feng in #53
• [Doc] Add roadmap to README.md by @Shaoting-Feng in #57
• Enable Dockerfile, Helm and shellcheck pre-commit hooks by @hmellor in #55
• Explain how pre-commit-manual job works by @hmellor in #58
• feat: Add ingress configuration to routerSpec by @0xThresh in #54
• [Add] customization support for runtimeClass by @ApostaC in #63
• fix: Update Helm values example to use new hf_token value by @0xThresh in #65
• [Doc] Add news to README.md by @Shaoting-Feng in #70
• [helm] Bumping the version of helm chart to trigger the auto release by @ApostaC in #72

New Contributors

• @dmatch01 made their first contribution in #29
• @hmellor made their first contribution in #35
• @dxu104 made their first contribution in #42
• @waltforme made their first contribution in #51

Full Changelog: vllm-stack-0.0.2...vllm-stack-0.0.3

vllm-stack-0.0.2

What's Changed

• Simplify the main README by @ApostaC in #1
• Update the name to vLLM Production Stack by @ApostaC in #3
• Update README.md by @ApostaC in #4
• Fix missing diagram in the readme and add roadmap by @ApostaC in #10
• Fix broken grafana screenshot by @ApostaC in #11
• 🐛 add namespace to router chart by @joerunde in #12
• Update README.md by @Hanchenli in #13
• feat: Support dynamic node changes in session router by @gaocegege in #18
• feat: Make router a python package by @gaocegege in #20
• feat: Add Github workflows to lint and release Helm chart by @0xThresh in #23
• fix(router): Support engine stats and request internal by @gaocegege in #21
• feat: Use secrets to configure HF_TOKEN by @ApostaC in #22

New Contributors

• @joerunde made their first contribution in #12
• @Hanchenli made their first contribution in #13

Full Changelog: https://github.com/vllm-project/production-stack/commits/vllm-stack-0.0.2