Merge similar examples in offline_inference into single basic exa…

…mple (#12737)

.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/basic.py"
+    python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m"
 
   # 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 -e HF_TOKEN -v /root/.cache/huggingface:/root/.cache/huggingface --name gh200-test --gpus=all --entrypoint="" gh200-test bash -c '
-    python3 examples/offline_inference/cli.py --model meta-llama/Llama-3.2-1B
+    python3 examples/offline_inference/basic/generate.py --model meta-llama/Llama-3.2-1B
 '

.buildkite/run-hpu-test.sh

@@ -20,5 +20,5 @@ trap remove_docker_container_and_exit 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/basic.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/generate.py --model facebook/opt-125m
 EXITCODE=$?

.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/basic.py
+docker run --network host --env VLLM_OPENVINO_KVCACHE_SPACE=1 --name openvino-test openvino-test python3 /workspace/examples/offline_inference/basic/generate.py --model facebook/opt-125m

.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/basic.py
-    python3 examples/offline_inference/cli.py -tp 2
+    python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m
+    python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m -tp 2
 '

.buildkite/test-pipeline.yaml

@@ -215,18 +215,18 @@ steps:
   - examples/
   commands:
     - pip install tensorizer # for tensorizer test
-    - python3 offline_inference/basic.py
-    - python3 offline_inference/cpu_offload.py
-    - python3 offline_inference/chat.py
+    - python3 offline_inference/basic/generate.py --model facebook/opt-125m
+    - python3 offline_inference/basic/generate.py --model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
+    - python3 offline_inference/basic/chat.py
     - python3 offline_inference/prefix_caching.py
     - python3 offline_inference/llm_engine_example.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/encoder_decoder.py
-    - python3 offline_inference/classification.py
-    - python3 offline_inference/embedding.py
-    - python3 offline_inference/scoring.py
+    - python3 offline_inference/basic/classify.py
+    - python3 offline_inference/basic/embed.py
+    - python3 offline_inference/basic/score.py
     - python3 offline_inference/profiling.py --model facebook/opt-125m run_num_steps --num-steps 2
 
 - label: Prefix Caching Test # 9min

docs/source/generate_examples.py

@@ -147,7 +147,7 @@ def generate(self) -> str:
             return content
 
         content += "## Example materials\n\n"
-        for file in self.other_files:
+        for file in sorted(self.other_files):
             include = "include" if file.suffix == ".md" else "literalinclude"
             content += f":::{{admonition}} {file.relative_to(self.path)}\n"
             content += ":class: dropdown\n\n"
@@ -194,7 +194,7 @@ def generate_examples():
             path=EXAMPLE_DOC_DIR / "examples_offline_inference_index.md",
             title="Offline Inference",
             description=
-            "Offline inference examples demonstrate how to use vLLM in an offline setting, where the model is queried for predictions in batches.",  # noqa: E501
+            "Offline inference examples demonstrate how to use vLLM in an offline setting, where the model is queried for predictions in batches. We recommend starting with <project:basic.md>.",  # noqa: E501
             caption="Examples",
         ),
     }

docs/source/getting_started/installation/cpu/index.md

@@ -170,7 +170,7 @@ vLLM CPU backend supports the following vLLM features:
 sudo apt-get install libtcmalloc-minimal4 # install TCMalloc library
 find / -name *libtcmalloc* # find the dynamic link library path
 export LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:$LD_PRELOAD # prepend the library to LD_PRELOAD
-python examples/offline_inference/basic.py # run vLLM
+python examples/offline_inference/basic/basic.py # run vLLM
 ```
 
 - When using the online serving, it is recommended to reserve 1-2 CPU cores for the serving framework to avoid CPU oversubscription. For example, on a platform with 32 physical CPU cores, reserving CPU 30 and 31 for the framework and using CPU 0-29 for OpenMP:
@@ -207,7 +207,7 @@ CPU NODE SOCKET CORE L1d:L1i:L2:L3 ONLINE    MAXMHZ   MINMHZ      MHZ
 
 # On this platform, it is recommend to only bind openMP threads on logical CPU cores 0-7 or 8-15
 $ export VLLM_CPU_OMP_THREADS_BIND=0-7
-$ python examples/offline_inference/basic.py
+$ python examples/offline_inference/basic/basic.py
 ```
 
 - If using vLLM CPU backend on a multi-socket machine with NUMA, be aware to set CPU cores using `VLLM_CPU_OMP_THREADS_BIND` to avoid cross NUMA node memory access.

docs/source/getting_started/quickstart.md

@@ -40,7 +40,7 @@ For non-CUDA platforms, please refer [here](#installation-index) for specific in
 
 ## Offline Batched Inference
 
-With vLLM installed, you can start generating texts for list of input prompts (i.e. offline batch inferencing). See the example script: <gh-file:examples/offline_inference/basic.py>
+With vLLM installed, you can start generating texts for list of input prompts (i.e. offline batch inferencing). See the example script: <gh-file:examples/offline_inference/basic/basic.py>
 
 The first line of this example imports the classes {class}`~vllm.LLM` and {class}`~vllm.SamplingParams`:
 

docs/source/models/generative_models.md

@@ -46,7 +46,7 @@ for output in outputs:
     print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
 ```
 
-A code example can be found here: <gh-file:examples/offline_inference/basic.py>
+A code example can be found here: <gh-file:examples/offline_inference/basic/basic.py>
 
 ### `LLM.beam_search`
 
@@ -103,7 +103,7 @@ for output in outputs:
     print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
 ```
 
-A code example can be found here: <gh-file:examples/offline_inference/chat.py>
+A code example can be found here: <gh-file:examples/offline_inference/basic/chat.py>
 
 If the model doesn't have a chat template or you want to specify another one,
 you can explicitly pass a chat template:

docs/source/models/pooling_models.md

@@ -88,7 +88,7 @@ embeds = output.outputs.embedding
 print(f"Embeddings: {embeds!r} (size={len(embeds)})")
 ```
 
-A code example can be found here: <gh-file:examples/offline_inference/embedding.py>
+A code example can be found here: <gh-file:examples/offline_inference/basic/embed.py>
 
 ### `LLM.classify`
 
@@ -103,7 +103,7 @@ probs = output.outputs.probs
 print(f"Class Probabilities: {probs!r} (size={len(probs)})")
 ```
 
-A code example can be found here: <gh-file:examples/offline_inference/classification.py>
+A code example can be found here: <gh-file:examples/offline_inference/basic/classify.py>
 
 ### `LLM.score`
 
@@ -125,7 +125,7 @@ score = output.outputs.score
 print(f"Score: {score}")
 ```
 
-A code example can be found here: <gh-file:examples/offline_inference/scoring.py>
+A code example can be found here: <gh-file:examples/offline_inference/basic/score.py>
 
 ## Online Serving
 

examples/offline_inference/basic/README.md

@@ -0,0 +1,94 @@
+# Basic
+
+The `LLM` class provides the primary Python interface for doing offline inference, which is interacting with a model without using a separate model inference server.
+
+## Usage
+
+The first script in this example shows the most basic usage of vLLM. If you are new to Python and vLLM, you should start here.
+
+```bash
+python examples/offline_inference/basic/basic.py
+```
+
+The rest of the scripts include an [argument parser](https://docs.python.org/3/library/argparse.html), which you can use to pass any arguments that are compatible with [`LLM`](https://docs.vllm.ai/en/latest/api/offline_inference/llm.html). Try running the script with `--help` for a list of all available arguments.
+
+```bash
+python examples/offline_inference/basic/classify.py
+```
+
+```bash
+python examples/offline_inference/basic/embed.py
+```
+
+```bash
+python examples/offline_inference/basic/score.py
+```
+
+The chat and generate scripts also accept the [sampling parameters](https://docs.vllm.ai/en/latest/api/inference_params.html#sampling-parameters): `max_tokens`, `temperature`, `top_p` and `top_k`.
+
+```bash
+python examples/offline_inference/basic/chat.py
+```
+
+```bash
+python examples/offline_inference/basic/generate.py
+```
+
+## Features
+
+In the scripts that support passing arguments, you can experiment with the following features.
+
+### Default generation config
+
+The `--generation-config` argument specifies where the generation config will be loaded from when calling `LLM.get_default_sampling_params()`. If set to ‘auto’, the generation config will be loaded from model path. If set to a folder path, the generation config will be loaded from the specified folder path. If it is not provided, vLLM defaults will be used.
+
+> If max_new_tokens is specified in generation config, then it sets a server-wide limit on the number of output tokens for all requests.
+
+Try it yourself with the following argument:
+
+```bash
+--generation-config auto
+```
+
+### Quantization
+
+#### AQLM
+
+vLLM supports models that are quantized using AQLM.
+
+Try one yourself by passing one of the following models to the `--model` argument:
+
+- `ISTA-DASLab/Llama-2-7b-AQLM-2Bit-1x16-hf`
+- `ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf`
+- `ISTA-DASLab/Llama-2-13b-AQLM-2Bit-1x16-hf`
+- `ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf`
+- `BlackSamorez/TinyLlama-1_1B-Chat-v1_0-AQLM-2Bit-1x16-hf`
+
+> Some of these models are likely to be too large for a single GPU. You can split them across multiple GPUs by setting `--tensor-parallel-size` to the number of required GPUs.
+
+#### GGUF
+
+vLLM supports models that are quantized using GGUF.
+
+Try one yourself by downloading a GUFF quantised model and using the following arguments:
+
+```python
+from huggingface_hub import hf_hub_download
+repo_id = "bartowski/Phi-3-medium-4k-instruct-GGUF"
+filename = "Phi-3-medium-4k-instruct-IQ2_M.gguf"
+print(hf_hub_download(repo_id, filename=filename))
+```
+
+```bash
+--model {local-path-printed-above} --tokenizer microsoft/Phi-3-medium-4k-instruct
+```
+
+### CPU offload
+
+The `--cpu-offload-gb` argument can be seen as a virtual way to increase the GPU memory size. For example, if you have one 24 GB GPU and set this to 10, virtually you can think of it as a 34 GB GPU. Then you can load a 13B model with BF16 weight, which requires at least 26GB GPU memory. Note that this requires fast CPU-GPU interconnect, as part of the model is loaded from CPU memory to GPU memory on the fly in each model forward pass.
+
+Try it yourself with the following arguments:
+
+```bash
+--model meta-llama/Llama-2-13b-chat-hf --cpu-offload-gb 10
+```