[Doc] Move examples into categories (#11840)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -452,9 +452,9 @@ 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/tensorize_vllm_model.py) This should still be faster than
|
||||
default HuggingFace loading, but will be slower than loading a
|
||||
vLLM-tensorized model.
|
||||
examples/other/tensorize_vllm_model.py) This should still
|
||||
be faster than default HuggingFace loading, but will be slower than
|
||||
loading a vLLM-tensorized model.
|
||||
"""
|
||||
device_config = vllm_config.device_config
|
||||
model_config = vllm_config.model_config
|
||||
@@ -472,7 +472,7 @@ class TensorizerLoader(BaseModelLoader):
|
||||
"""Load a serialized model with tensorizer.
|
||||
|
||||
Expects a vLLM-tensorized model. See the
|
||||
examples/tensorize_vllm_model.py example script
|
||||
examples/other/tensorize_vllm_model.py example script
|
||||
for serializing vLLM models."""
|
||||
|
||||
device_config = vllm_config.device_config
|
||||
@@ -529,7 +529,8 @@ class ShardedStateLoader(BaseModelLoader):
|
||||
Model loader that directly loads each worker's model state dict, which
|
||||
enables a fast load path for large tensor-parallel models where each worker
|
||||
only needs to read its own shard rather than the entire checkpoint. See
|
||||
`examples/save_sharded_state.py` for creating a sharded checkpoint.
|
||||
`examples/offline_inference/save_sharded_state.py` for creating a sharded
|
||||
checkpoint.
|
||||
"""
|
||||
|
||||
DEFAULT_PATTERN = "model-rank-{rank}-part-{part}.safetensors"
|
||||
|
||||
@@ -155,7 +155,7 @@ 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/tensorize_vllm_model.py.
|
||||
examples/other/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
|
||||
@@ -363,12 +363,12 @@ class TensorizerAgent:
|
||||
def tensorizer_weights_iterator(
|
||||
tensorizer_args: "TensorizerArgs"
|
||||
) -> Generator[Tuple[str, torch.Tensor], None, None]:
|
||||
logger.warning(
|
||||
"Deserializing HuggingFace models is not optimized for "
|
||||
"loading on vLLM, as tensorizer is forced to load to CPU. "
|
||||
"Consider deserializing a vLLM model instead for faster "
|
||||
"load times. See the examples/tensorize_vllm_model.py example "
|
||||
"script for serializing vLLM models.")
|
||||
logger.warning("Deserializing HuggingFace models is not optimized for "
|
||||
"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 "
|
||||
"for serializing vLLM models.")
|
||||
|
||||
deserializer_args = tensorizer_args.deserializer_params
|
||||
stream_params = tensorizer_args.stream_params
|
||||
|
||||
@@ -503,7 +503,8 @@ def kv_cache_scales_loader(
|
||||
KV cache scaling factors. The serialization should represent a dictionary
|
||||
whose keys are the TP ranks and values are another dictionary mapping layers
|
||||
to their KV cache scaling factors.
|
||||
Keep this function in sync with the output of examples/fp8/extract_scales.py
|
||||
Keep this function in sync with the output of
|
||||
examples/other/fp8/extract_scales.py
|
||||
"""
|
||||
try:
|
||||
with open(filename) as f:
|
||||
|
||||
Reference in New Issue
Block a user