Merge branch 'main' into feature/router-hpa

# Conflicts:
#	helm/values.yaml

Author: BrianPark314

.github/PULL_REQUEST_TEMPLATE.md

@@ -6,7 +6,7 @@ FIX #xxxx (*link existing issues this PR will resolve*)
 
 ---
 
-- [ ] Make sure the code changes pass the [pre-commit](../CONTRIBUTING.md) checks.
+- [ ] Make sure the code changes pass the [pre-commit](https://github.com/vllm-project/production-stack/blob/main/CONTRIBUTING.md) checks.
 - [ ] Sign-off your commit by using <code>-s</code> when doing <code>git commit</code>
 - [ ] Try to classify PRs for easy understanding of the type of changes, such as `[Bugfix]`, `[Feat]`, and `[CI]`.
 

.github/workflows/functionality-helm-chart.yml

@@ -66,7 +66,7 @@ jobs:
       - name: Validate the installation and send query to the stack
         run: |
           bash .github/port-forward.sh curl-05-secure-vllm
-        timeout-minutes: 2
+        timeout-minutes: 3
       - name: Archive functionality results
         uses: actions/upload-artifact@v4
         if: always()
@@ -112,7 +112,7 @@ jobs:
       - name: Validate the installation and send query to the stack
         run: |
           bash .github/port-forward.sh curl-02-two-pods
-        timeout-minutes: 2
+        timeout-minutes: 3
       - name: Archive functionality results
         uses: actions/upload-artifact@v4
         if: always()
@@ -156,7 +156,7 @@ jobs:
       - name: Validate the installation and send query to the stack
         run: |
           bash .github/port-forward.sh curl-04-multiple-models
-        timeout-minutes: 3
+        timeout-minutes: 5
       - name: Archive functionality results
         uses: actions/upload-artifact@v4
         if: always()

.github/workflows/pre-commit.yml

@@ -16,7 +16,7 @@ jobs:
     - run: echo "::add-matcher::.github/workflows/matchers/actionlint.json"
     - uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd # v3.0.1
     - run: pip install ruff
-    - run: ruff check src/tests
+    - run: ruff check src
 
   pre-commit-manual:
     strategy:

.github/workflows/router-e2e-test.yml

@@ -109,13 +109,10 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v4
 
-      - name: Setup Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
       - name: Install Python dependencies
         run: |
+          source /usr/local/bin/conda-init
+          conda activate llmstack
           python -m pip install --upgrade pip
           pip install -r benchmarks/multi-round-qa/requirements.txt
           pip install -e .
@@ -142,6 +139,8 @@ jobs:
 
       - name: Run all k8s discovery routing tests
         run: |
+          source /usr/local/bin/conda-init
+          conda activate llmstack
           echo "🧪 Running all k8s discovery routing tests"
           ./tests/e2e/run-k8s-routing-test.sh all \
             --model "facebook/opt-125m" \
@@ -173,23 +172,24 @@ jobs:
       - name: Check out repository code
         uses: actions/checkout@v4
 
-      - name: Setup Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
       - name: Install Python dependencies
         run: |
+          source /usr/local/bin/conda-init
+          conda activate llmstack
           python -m pip install --upgrade pip
           pip install -e .
 
       - name: Install vLLM and lmcache
         run: |
+          source /usr/local/bin/conda-init
+          conda activate llmstack
           pip install vllm
           pip install lmcache
 
       - name: Start 2 vLLM serve backends
         run: |
+          source /usr/local/bin/conda-init
+          conda activate llmstack
           echo "🚀 Starting vLLM serve backend"
           mkdir -p "$LOG_DIR"
           CUDA_VISIBLE_DEVICES=0 vllm serve facebook/opt-125m --port 8001 --gpu-memory-utilization 0.7 --chat-template .github/template-chatml.jinja > "$LOG_DIR/backend1.log" 2>&1 &
@@ -202,9 +202,9 @@ jobs:
           ./tests/e2e/wait-for-backends.sh 180 "http://localhost:8001" "http://localhost:8002"
 
       - name: Run All Static Discovery Routing Tests
-        env:
-          PYTHONPATH: ${{ github.workspace }}/src
         run: |
+          source /usr/local/bin/conda-init
+          conda activate llmstack
           echo "🧪 Running all static discovery routing tests sequentially"
           chmod +x tests/e2e/run-static-discovery-routing-test.sh
           ./tests/e2e/run-static-discovery-routing-test.sh all \

README.md

@@ -11,11 +11,11 @@
 
 ## Community Events
 
-We host **weekly** community meetings at **alternating** times to accommodate different time zones.
+We host **weekly** community meetings at the following timeslot:
 
-- Tuesdays at 6:00 PM PT – [Add to Calendar](https://drive.usercontent.google.com/u/0/uc?id=1iKpFrt-grVZSIbIXpnVlZyEvADcxLMj_&export=download)
+- Tuesdays at 5:30 PM PT – [Add to Calendar](https://drive.usercontent.google.com/u/0/uc?id=1E4rcnwZHV84IEFXAGtJ-TP3o1rslNDei&export=download)
 
-Meetings alternate weekly between the two times. All are welcome to join!
+All are welcome to join!
 
 ## Introduction
 

docs/source/benchmarks/multiround-qa.rst

@@ -0,0 +1,11 @@
+Community Meetings
+==================
+
+Community Events
+----------------
+
+We host bi-weekly community meetings at the following timeslot:
+
+**Every other Tuesday at 5:30 PM PT starting July 29th** – `Add to Calendar <https://github.com/vllm-project/production-stack/blob/main/community/prod_stack_community_meeting.ics>`_
+
+All are welcome to join!