[Doc] Rename offline inference examples (#11927)

Signed-off-by: Harry Mellor <[email protected]>

Author: hmellor

.buildkite/run-cpu-test.sh

@@ -30,7 +30,7 @@ function cpu_tests() {
   # offline inference
   docker exec cpu-test-"$BUILDKITE_BUILD_NUMBER"-avx2-"$NUMA_NODE" bash -c "
     set -e
-    python3 examples/offline_inference/offline_inference.py"
+    python3 examples/offline_inference/basic.py"
 
   # Run basic model test
   docker exec cpu-test-"$BUILDKITE_BUILD_NUMBER"-"$NUMA_NODE" bash -c "

.buildkite/run-gh200-test.sh

@@ -24,5 +24,5 @@ remove_docker_container
 
 # Run the image and test offline inference
 docker run --name gh200-test --gpus=all --entrypoint="" gh200-test bash -c '
-    python3 examples/offline_inference/offline_inference.py
+    python3 examples/offline_inference/basic.py
 '

.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 HABANA_VISIBLE_DEVICES=all -e VLLM_SKIP_WARMUP=true --entrypoint="" hpu-test-env python3 examples/offline_inference/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/basic.py

.buildkite/run-neuron-test.sh

@@ -51,4 +51,4 @@ docker run --rm -it --device=/dev/neuron0 --device=/dev/neuron1 --network host \
        -e "NEURON_COMPILE_CACHE_URL=${NEURON_COMPILE_CACHE_MOUNT}" \
        --name "${container_name}" \
        ${image_name} \
-       /bin/bash -c "python3 /workspace/vllm/examples/offline_inference/offline_inference_neuron.py"
+       /bin/bash -c "python3 /workspace/vllm/examples/offline_inference/neuron.py"

.buildkite/run-openvino-test.sh

@@ -13,4 +13,4 @@ trap remove_docker_container EXIT
 remove_docker_container
 
 # Run the image and launch offline inference
-docker run --network host --env VLLM_OPENVINO_KVCACHE_SPACE=1 --name openvino-test openvino-test python3 /workspace/examples/offline_inference/offline_inference.py
+docker run --network host --env VLLM_OPENVINO_KVCACHE_SPACE=1 --name openvino-test openvino-test python3 /workspace/examples/offline_inference/basic.py

.buildkite/run-tpu-test.sh

@@ -23,4 +23,4 @@ docker run --privileged --net host --shm-size=16G -it \
     && pytest -v -s /workspace/vllm/tests/tpu/test_custom_dispatcher.py \
     && python3 /workspace/vllm/tests/tpu/test_compilation.py \
     && python3 /workspace/vllm/tests/tpu/test_quantization_accuracy.py \
-    && python3 /workspace/vllm/examples/offline_inference/offline_inference_tpu.py"
+    && python3 /workspace/vllm/examples/offline_inference/tpu.py"

.buildkite/run-xpu-test.sh

@@ -14,6 +14,6 @@ remove_docker_container
 
 # Run the image and test offline inference/tensor parallel
 docker run --name xpu-test --device /dev/dri -v /dev/dri/by-path:/dev/dri/by-path --entrypoint="" xpu-test sh -c '
-    python3 examples/offline_inference/offline_inference.py
-    python3 examples/offline_inference/offline_inference_cli.py -tp 2
+    python3 examples/offline_inference/basic.py
+    python3 examples/offline_inference/cli.py -tp 2
 '

.buildkite/test-pipeline.yaml

@@ -187,19 +187,19 @@ steps:
   - examples/
   commands:
     - pip install tensorizer # for tensorizer test
-    - python3 offline_inference/offline_inference.py
+    - python3 offline_inference/basic.py
     - python3 offline_inference/cpu_offload.py
-    - python3 offline_inference/offline_inference_chat.py
-    - python3 offline_inference/offline_inference_with_prefix.py
+    - python3 offline_inference/chat.py
+    - python3 offline_inference/prefix_caching.py
     - python3 offline_inference/llm_engine_example.py
-    - python3 offline_inference/offline_inference_vision_language.py
-    - python3 offline_inference/offline_inference_vision_language_multi_image.py
+    - python3 offline_inference/vision_language.py
+    - python3 offline_inference/vision_language_multi_image.py
     - python3 other/tensorize_vllm_model.py --model facebook/opt-125m serialize --serialized-directory /tmp/ --suffix v1 && python3 other/tensorize_vllm_model.py --model facebook/opt-125m deserialize --path-to-tensors /tmp/vllm/facebook/opt-125m/v1/model.tensors
-    - python3 offline_inference/offline_inference_encoder_decoder.py
-    - python3 offline_inference/offline_inference_classification.py
-    - python3 offline_inference/offline_inference_embedding.py
-    - python3 offline_inference/offline_inference_scoring.py
-    - python3 offline_inference/offline_profile.py --model facebook/opt-125m run_num_steps --num-steps 2
+    - python3 offline_inference/encoder_decoder.py
+    - python3 offline_inference/classification.py
+    - python3 offline_inference/embedding.py
+    - python3 offline_inference/scoring.py
+    - python3 offline_inference/profiling.py --model facebook/opt-125m run_num_steps --num-steps 2
 
 - label: Prefix Caching Test # 9min
   mirror_hardwares: [amd]