[DO NOT MERGE] Ibm dev rebased

.buildkite/run-hpu-test.sh

@@ -13,4 +13,4 @@ trap remove_docker_container EXIT
 remove_docker_container
 
 # Run the image and launch offline inference
-docker run --runtime=habana --name=hpu-test --network=host -e VLLM_SKIP_WARMUP=true --entrypoint="" hpu-test-env python3 examples/offline_inference.py
+docker run --runtime=habana --name=hpu-test --network=host -e HABANA_VISIBLE_DEVICES=all -e VLLM_SKIP_WARMUP=true --entrypoint="" hpu-test-env python3 examples/offline_inference.py

.github/CODEOWNERS

@@ -3,13 +3,16 @@
 
 # This lists cover the "core" components of vLLM that require careful review
 /vllm/attention/backends/abstract.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
-/vllm/core @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
-/vllm/engine/llm_engine.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
-/vllm/executor/executor_base.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
-/vllm/worker/worker_base.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
-/vllm/worker/worker.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
-/vllm/model_executor/layers/sampler.py @WoosukKwon @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
-CMakeLists.txt @tlrmchlsmth @WoosukKwon
+/vllm/core @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+/vllm/engine/llm_engine.py @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+/vllm/executor/executor_base.py @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+/vllm/worker/worker_base.py @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+/vllm/worker/worker.py @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+/vllm/model_executor/layers/sampler.py @zhuohan123 @youkaichao @alexm-neuralmagic @comaniac @njhill
+CMakeLists.txt @tlrmchlsmth
+
+# vLLM V1
+/vllm/v1 @WoosukKwon @robertgshaw2-neuralmagic @njhill @ywang96 @comaniac @alexm-neuralmagic
 
 # Test ownership
 /tests/async_engine @njhill @robertgshaw2-neuralmagic @simon-mo

.github/FUNDING.yml

@@ -1,2 +1,2 @@
 github: [vllm-project]
-open_collective: [vllm]
+open_collective: vllm

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,5 @@
+FILL IN THE PR DESCRIPTION HERE
+
+FIX #xxxx (*link existing issues this PR will resolve*)
+
+**BEFORE SUBMITTING, PLEASE READ https://docs.vllm.ai/en/latest/contributing/overview.html **

.github/scripts/cleanup_pr_body.sh

@@ -15,19 +15,36 @@ NEW=/tmp/new_pr_body.txt
 gh pr view --json body --template "{{.body}}" "${PR_NUMBER}" > "${OLD}"
 cp "${OLD}" "${NEW}"
 
-# Remove all lines after and including "**BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE**"
-sed -i '/\*\*BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE\*\*/,$d' "${NEW}"
-
 # Remove "FIX #xxxx (*link existing issues this PR will resolve*)"
 sed -i '/FIX #xxxx.*$/d' "${NEW}"
 
 # Remove "FILL IN THE PR DESCRIPTION HERE"
 sed -i '/FILL IN THE PR DESCRIPTION HERE/d' "${NEW}"
 
+# Remove all lines after and including "**BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE**"
+sed -i '/\*\*BEFORE SUBMITTING, PLEASE READ.*\*\*/,$d' "${NEW}"
+
+# Remove HTML <details> section that includes <summary> text of "PR Checklist (Click to Expand)"
+python3 - <<EOF
+import re
+
+with open("${NEW}", "r") as file:
+    content = file.read()
+
+pattern = re.compile(r'(---\n\n)?<details>.*?<summary>.*?PR Checklist \(Click to Expand\).*?</summary>.*?</details>', re.DOTALL)
+content = re.sub(pattern, '', content)
+
+with open("${NEW}", "w") as file:
+    file.write(content)
+EOF
+
 # Run this only if ${NEW} is different than ${OLD}
 if ! cmp -s "${OLD}" "${NEW}"; then
-    echo "Updating PR body"
     gh pr edit --body-file "${NEW}" "${PR_NUMBER}"
+    echo
+    echo "Updated PR body:"
+    echo
+    cat "${NEW}"
 else
     echo "No changes needed"
 fi

Dockerfile.ubi

@@ -201,15 +201,19 @@ WORKDIR /home/vllm
 
 ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
 
-
 FROM vllm-openai as vllm-grpc-adapter
 
 USER root
 
 RUN --mount=type=cache,target=/root/.cache/pip \
     --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,from=build,src=/workspace/dist,target=/workspace/dist \
-    HOME=/root uv pip install $(echo dist/*.whl)'[tensorizer]' vllm-tgis-adapter==0.5.3
+    uv pip install $(echo /workspace/dist/*.whl)'[tensorizer]'  --verbose && \
+    uv pip install \
+        "git+https://github.com/opendatahub-io/vllm-tgis-adapter@ibm-20241106-adapter" --verbose
+
+RUN --mount=type=bind,from=build,src=/workspace/dist,target=/workspace/dist \
+    echo "Local dir and dist:" && pwd && ls -l /workspace/dist
 
 ENV GRPC_PORT=8033 \
     PORT=8000 \

README.md

@@ -100,6 +100,7 @@ vLLM is a community project. Our compute resources for development and testing a
 - Dropbox
 - Google Cloud
 - Lambda Lab
+- Nebius
 - NVIDIA
 - Replicate
 - Roblox

benchmarks/benchmark_serving.py

@@ -251,6 +251,19 @@ def sample_hf_requests(
                     "url": f"data:image/jpeg;base64,{image_base64}"
                 },
             }
+        elif "image" in data and isinstance(data["image"], str):
+            if (data["image"].startswith("http://") or \
+                data["image"].startswith("file://")):
+                image_url = data["image"]
+            else:
+                image_url = f"file://{data['image']}"
+
+            mm_content = {
+                "type": "image_url",
+                "image_url": {
+                    "url": image_url
+                },
+            }
         else:
             mm_content = None