[Doc] Move examples and further reorganize user guide (#18666)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

examples/other/tensorize_vllm_model.py → examples/others/tensorize_vllm_model.py

@@ -28,7 +28,7 @@ https://github.com/coreweave/tensorizer
 To serialize a model, install vLLM from source, then run something 
 like this from the root level of this repository:
 
-python examples/other/tensorize_vllm_model.py \
+python examples/others/tensorize_vllm_model.py \
    --model facebook/opt-125m \
    serialize \
    --serialized-directory s3://my-bucket \
@@ -48,7 +48,7 @@ providing a `--keyfile` argument.
 To deserialize a model, you can run something like this from the root 
 level of this repository:
 
-python examples/other/tensorize_vllm_model.py \
+python examples/others/tensorize_vllm_model.py \
    --model EleutherAI/gpt-j-6B \
    --dtype float16 \
    deserialize \
@@ -66,11 +66,11 @@ shard's rank. Sharded models serialized with this script will be named as
 model-rank-%03d.tensors
 
 For more information on the available arguments for serializing, run 
-`python -m examples.other.tensorize_vllm_model serialize --help`.
+`python -m examples.others.tensorize_vllm_model serialize --help`.
 
 Or for deserializing:
 
-`python examples/other/tensorize_vllm_model.py deserialize --help`.
+`python examples/others/tensorize_vllm_model.py deserialize --help`.
 
 Once a model is serialized, tensorizer can be invoked with the `LLM` class 
 directly to load models:
@@ -91,7 +91,7 @@ TensorizerConfig arguments desired.
 In order to see all of the available arguments usable to configure 
 loading with tensorizer that are given to `TensorizerConfig`, run:
 
-`python examples/other/tensorize_vllm_model.py deserialize --help`
+`python examples/others/tensorize_vllm_model.py deserialize --help`
 
 under the `tensorizer options` section. These can also be used for
 deserialization in this example script, although `--tensorizer-uri` and

pyproject.toml

@@ -62,11 +62,6 @@ ignore_patterns = [
 [tool.ruff]
 # Allow lines to be as long as 80.
 line-length = 80
-exclude = [
-    # External file, leaving license intact
-    "examples/other/fp8/quantizer/quantize.py",
-    "vllm/vllm_flash_attn/flash_attn_interface.pyi"
-]
 
 [tool.ruff.lint.per-file-ignores]
 "vllm/third_party/**" = ["ALL"]

requirements/common.txt

@@ -41,7 +41,7 @@ compressed-tensors == 0.9.4 # required for compressed-tensors
 depyf==0.18.0 # required for profiling and debugging with compilation config
 cloudpickle # allows pickling lambda functions in model_executor/models/registry.py
 watchfiles # required for http server to monitor the updates of TLS files
-python-json-logger # Used by logging as per examples/other/logging_configuration.md
+python-json-logger # Used by logging as per examples/others/logging_configuration.md
 scipy # Required for phi-4-multimodal-instruct
 ninja # Required for xgrammar, rocm, tpu, xpu
 opentelemetry-sdk>=1.26.0  # vllm.tracing

tests/lora/test_llama_tp.py

@@ -207,7 +207,7 @@ def test_tp2_serialize_and_deserialize_lora(tmp_path, sql_lora_files,
     try:
         result = subprocess.run([
             sys.executable,
-            f"{VLLM_PATH}/examples/other/tensorize_vllm_model.py", "--model",
+            f"{VLLM_PATH}/examples/others/tensorize_vllm_model.py", "--model",
             MODEL_PATH, "--lora-path", lora_path, "--tensor-parallel-size",
             str(tp_size), "serialize", "--serialized-directory",
             str(tmp_path), "--suffix", suffix

vllm/model_executor/model_loader/tensorizer.py

@@ -251,7 +251,7 @@ class TensorizerArgs:
       encryption_keyfile: File path to a binary file containing a  
           binary key to use for decryption. `None` (the default) means 
           no decryption. See the example script in 
-          examples/other/tensorize_vllm_model.py. 
+          examples/others/tensorize_vllm_model.py. 
       s3_access_key_id: The access key for the S3 bucket. Can also be set via
           the S3_ACCESS_KEY_ID environment variable.
       s3_secret_access_key: The secret access key for the S3 bucket. Can also
@@ -469,7 +469,7 @@ def tensorizer_weights_iterator(
                    "loading on vLLM, as tensorizer is forced to load to CPU. "
                    "Consider deserializing a vLLM model instead for faster "
                    "load times. See the "
-                   "examples/other/tensorize_vllm_model.py example script "
+                   "examples/others/tensorize_vllm_model.py example script "
                    "for serializing vLLM models.")
 
     deserializer_args = tensorizer_args.deserializer_params

vllm/model_executor/model_loader/tensorizer_loader.py

@@ -48,7 +48,7 @@ class TensorizerLoader(BaseModelLoader):
         """Load a serialized model with tensorizer to the CPU.
 
         This is only necessary when the model isn't vLLM-tensorized (see
-        examples/other/tensorize_vllm_model.py) This should still
+        examples/others/tensorize_vllm_model.py) This should still
         be faster than default HuggingFace loading, but will be slower than
         loading a vLLM-tensorized model.
         """
@@ -68,7 +68,7 @@ class TensorizerLoader(BaseModelLoader):
         """Load a serialized model with tensorizer.
 
         Expects a vLLM-tensorized model. See the
-        examples/other/tensorize_vllm_model.py example script
+        examples/others/tensorize_vllm_model.py example script
         for serializing vLLM models."""
 
         device_config = vllm_config.device_config