[Examples][last/6] Resettle examples. (#41084)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-05-07 19:42:12 -07:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 57c2f724c1
commit 1d694e78c9
61 changed files with 60 additions and 88 deletions
@@ -211,7 +211,7 @@ class TensorizerConfig(MutableMapping):
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/others/tensorize_vllm_model.py.
examples/features/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
@@ -579,7 +579,7 @@ 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/others/tensorize_vllm_model.py example script "
"examples/features/tensorize_vllm_model.py example script "
"for serializing vLLM models."
)
@@ -73,7 +73,7 @@ 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/others/tensorize_vllm_model.py) This should still
examples/features/tensorize_vllm_model.py) This should still
be faster than default HuggingFace loading, but will be slower than
loading a vLLM-tensorized model.
"""
@@ -104,7 +104,7 @@ class TensorizerLoader(BaseModelLoader):
"""Load serialized model weights with tensorizer.
Expects a vLLM-tensorized model. See the
examples/others/tensorize_vllm_model.py example script
examples/features/tensorize_vllm_model.py example script
for serializing vLLM models."""
if is_vllm_tensorized(self.tensorizer_config):
tensorizer_config = self._patch_tensorizer_config(model_config)