llmeter 0.1.0__tar.gz

llmeter-0.1.0/LICENSE

@@ -0,0 +1,175 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.

llmeter-0.1.0/NOTICE

@@ -0,0 +1 @@
+Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.

llmeter-0.1.0/PKG-INFO

@@ -0,0 +1,125 @@
+Metadata-Version: 2.1
+Name: llmeter
+Version: 0.1.0
+Summary: A lightweight, cross-platform latency and throughput profiler for LLMs
+License: Apache-2.0
+Keywords: llm,genai,testing,performance
+Author: Amazon Web Services
+Maintainer: llmeter-maintainers
+Maintainer-email: llmeter-maintainers@amazon.com
+Requires-Python: >=3.10,<3.13
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Provides-Extra: all
+Provides-Extra: litellm
+Provides-Extra: openai
+Provides-Extra: plotting
+Requires-Dist: boto3 (>=1.34.129)
+Requires-Dist: fsspec[http,s3] (>=2023.6.0)
+Requires-Dist: jmespath (>=0.7.1,<2.0.0)
+Requires-Dist: litellm (>=1.47.1) ; extra == "all" or extra == "litellm"
+Requires-Dist: openai (>=1.35.1) ; extra == "all" or extra == "openai"
+Requires-Dist: seaborn (>=0.13.2) ; extra == "all" or extra == "plotting"
+Requires-Dist: tqdm (>=4.66.0)
+Requires-Dist: universal-pathlib (>=0.2.1)
+Description-Content-Type: text/markdown
+
+<div align="center">
+<img alt="LLMeter (Logo)" src="docs/llmeter-logotype-192px.png" height="96px" width="396px"/>
+
+**Measuring large language models latency and throughput**
+
+[![Latest Version](https://img.shields.io/pypi/v/llmeter.svg)](https://pypi.python.org/pypi/llmeter)
+[![Supported Python Versions](https://img.shields.io/pypi/pyversions/llmeter)](https://pypi.python.org/pypi/llmeter)
+[![Code Style: Ruff](https://img.shields.io/badge/code_style-ruff-000000.svg)](https://github.com/astral-sh/ruff)
+
+</div>
+
+LLMeter is a pure-python library for simple latency and throughput testing of large language models (LLMs). It's designed to be lightweight to install; straightforward to run standard tests; and versatile to integrate - whether in notebooks, CI/CD, or other workflows.
+
+
+## :hammer_and_wrench: Installation
+
+LLMeter requires `python>=3.10`, please make sure your current version of python is compatible.
+
+To install the basic metering functionalities, you can install the minimum package using pip install:
+
+```terminal
+pip install llmeter
+```
+
+LLMeter also offers extra features that require additional dependencies. Currently these extras include:
+
+- **plotting**: Add methods to generate charts and heatmaps to summarize the results
+- **openai**: Enable testing endpoints offered by OpenAI
+- **litellm**: Enable testing a range of different models through [LiteLLM](https://github.com/BerriAI/litellm)
+
+You can install one or more of these extra options using pip:
+
+```terminal
+pip install llmeter[plotting, openai, litellm]
+```
+
+## :rocket: Quick-start
+
+At a high level, you'll start by configuring an LLMeter "Endpoint" for whatever type of LLM you're connecting to:
+
+```python
+# For example with Amazon Bedrock...
+from llmeter.endpoints import BedrockConverse
+endpoint = BedrockConverse(model_id="...")
+
+# ...or OpenAI...
+from llmeter.endpoints import OpenAIEndpoint
+endpoint = OpenAIEndpoint(model_id="...", api_key="...")
+
+# ...or via LiteLLM...
+from llmeter.endpoints import LiteLLM
+endpoint = LiteLLM("{provider}/{model_id}")
+
+# ...and so on
+```
+
+You can then run the high-level "experiments" offered by LLMeter:
+
+```python
+# For example a heatmap of latency by input & output token count:
+from llmeter.experiments import LatencyHeatmap
+latency_heatmap = LatencyHeatmap(
+    endpoint=endpoint,
+    clients=10,
+    source_file="examples/MaryShelleyFrankenstein.txt",
+    ...
+)
+heatmap_results = await latency_heatmap.run()
+latency_heatmap.plot_heatmap()
+
+# ...Or testing how throughput varies with concurrent request count:
+from llmeter.experiments import LoadTest
+sweep_test = LoadTest(
+    endpoint=endpoint,
+    payload={...},
+    sequence_of_clients=[1, 5, 20, 50, 100, 500],
+)
+sweep_results = await sweep_test.run()
+sweep_test.plot_sweep_results()
+```
+
+Alternatively, you can use the low-level `llmeter.runner.Runner` class to run and analyze request
+batches - and build your own custom experiments.
+
+For more details, check out our selection of end-to-end code examples in the [examples](examples) folder!
+
+
+## Security
+
+See [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.
+
+
+## License
+
+This project is licensed under the Apache-2.0 License.
+

llmeter-0.1.0/README.md

@@ -0,0 +1,95 @@
+<div align="center">
+<img alt="LLMeter (Logo)" src="docs/llmeter-logotype-192px.png" height="96px" width="396px"/>
+
+**Measuring large language models latency and throughput**
+
+[![Latest Version](https://img.shields.io/pypi/v/llmeter.svg)](https://pypi.python.org/pypi/llmeter)
+[![Supported Python Versions](https://img.shields.io/pypi/pyversions/llmeter)](https://pypi.python.org/pypi/llmeter)
+[![Code Style: Ruff](https://img.shields.io/badge/code_style-ruff-000000.svg)](https://github.com/astral-sh/ruff)
+
+</div>
+
+LLMeter is a pure-python library for simple latency and throughput testing of large language models (LLMs). It's designed to be lightweight to install; straightforward to run standard tests; and versatile to integrate - whether in notebooks, CI/CD, or other workflows.
+
+
+## :hammer_and_wrench: Installation
+
+LLMeter requires `python>=3.10`, please make sure your current version of python is compatible.
+
+To install the basic metering functionalities, you can install the minimum package using pip install:
+
+```terminal
+pip install llmeter
+```
+
+LLMeter also offers extra features that require additional dependencies. Currently these extras include:
+
+- **plotting**: Add methods to generate charts and heatmaps to summarize the results
+- **openai**: Enable testing endpoints offered by OpenAI
+- **litellm**: Enable testing a range of different models through [LiteLLM](https://github.com/BerriAI/litellm)
+
+You can install one or more of these extra options using pip:
+
+```terminal
+pip install llmeter[plotting, openai, litellm]
+```
+
+## :rocket: Quick-start
+
+At a high level, you'll start by configuring an LLMeter "Endpoint" for whatever type of LLM you're connecting to:
+
+```python
+# For example with Amazon Bedrock...
+from llmeter.endpoints import BedrockConverse
+endpoint = BedrockConverse(model_id="...")
+
+# ...or OpenAI...
+from llmeter.endpoints import OpenAIEndpoint
+endpoint = OpenAIEndpoint(model_id="...", api_key="...")
+
+# ...or via LiteLLM...
+from llmeter.endpoints import LiteLLM
+endpoint = LiteLLM("{provider}/{model_id}")
+
+# ...and so on
+```
+
+You can then run the high-level "experiments" offered by LLMeter:
+
+```python
+# For example a heatmap of latency by input & output token count:
+from llmeter.experiments import LatencyHeatmap
+latency_heatmap = LatencyHeatmap(
+    endpoint=endpoint,
+    clients=10,
+    source_file="examples/MaryShelleyFrankenstein.txt",
+    ...
+)
+heatmap_results = await latency_heatmap.run()
+latency_heatmap.plot_heatmap()
+
+# ...Or testing how throughput varies with concurrent request count:
+from llmeter.experiments import LoadTest
+sweep_test = LoadTest(
+    endpoint=endpoint,
+    payload={...},
+    sequence_of_clients=[1, 5, 20, 50, 100, 500],
+)
+sweep_results = await sweep_test.run()
+sweep_test.plot_sweep_results()
+```
+
+Alternatively, you can use the low-level `llmeter.runner.Runner` class to run and analyze request
+batches - and build your own custom experiments.
+
+For more details, check out our selection of end-to-end code examples in the [examples](examples) folder!
+
+
+## Security
+
+See [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.
+
+
+## License
+
+This project is licensed under the Apache-2.0 License.

llmeter-0.1.0/llmeter/endpoints/__init__.py

@@ -0,0 +1,13 @@
+import importlib.util
+
+from .base import Endpoint, InvocationResponse  # noqa: F401
+from .bedrock import BedrockConverse, BedrockConverseStream  # noqa: F401
+from .sagemaker import SageMakerEndpoint, SageMakerStreamEndpoint  # noqa: F401
+
+spec = importlib.util.find_spec("openai")
+if spec:
+    from .openai import OpenAIEndpoint, OpenAICompletionEndpoint  # noqa: F401
+
+spec = importlib.util.find_spec("litellm")
+if spec:
+    from .litellm import LiteLLM, LiteLLMStreaming  # noqa: F401

llmeter-0.1.0/llmeter/endpoints/base.py

@@ -0,0 +1,232 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+import importlib
+import json
+import os
+from abc import ABC, abstractmethod
+from dataclasses import asdict, dataclass
+from typing import Dict, TypeVar
+from uuid import uuid4
+
+from upath import UPath as Path
+
+Self = TypeVar(
+    "Self", bound="Endpoint"
+)  # for python >= 3.11 can be replaced with direct import of `Self`
+
+
+@dataclass
+class InvocationResponse:
+    """
+    A class representing a invocation result.
+
+    Attributes:
+        response_text (str): The invocation output.
+        id (str): A unique identifier for the invocation.
+        time_to_last_token (float): The time taken to generate the response in seconds.
+        time_to_first_token (float): The time taken to receive the first token of the response in seconds.
+        num_tokens_output (Optional[int]): The number of tokens in the response.
+        num_tokens_input (Optional[int]): The number of tokens in the invocation payload.
+        input_prompt (str): The input prompt used in the invocation.
+        time_per_output_token (float): The average time taken to generate each token in the response.
+        error (str): Any error that occurred during invocation.
+    """
+
+    response_text: str | None
+    id: str | None = None
+    input_prompt: str | None = None
+    time_to_first_token: float | None = None
+    time_to_last_token: float | None = None
+    num_tokens_input: int | None = None
+    num_tokens_output: int | None = None
+    time_per_output_token: float | None = None
+    error: str | None = None
+
+    def to_json(self, **kwargs) -> str:
+        return json.dumps(self.__dict__, **kwargs)
+
+    @staticmethod
+    def error_output(
+        input_prompt: str | None = None, error=None, id: str | None = None
+    ):
+        return InvocationResponse(
+            id=id or uuid4().hex,
+            response_text=None,
+            input_prompt=input_prompt,
+            time_to_last_token=None,
+            error="invocation failed" if error is None else str(error),
+        )
+
+    def __repr__(self):
+        return self.to_json(default=str)
+
+    def __str__(self):
+        return self.to_json(indent=4, default=str)
+
+    def to_dict(self):
+        return asdict(self)
+
+
+class Endpoint(ABC):
+    """
+    An abstract base class for endpoint implementations.
+
+    This class defines the basic structure and interface for all endpoint classes.
+    It provides abstract methods that must be implemented by subclasses.
+    """
+
+    @abstractmethod
+    def __init__(
+        self,
+        endpoint_name: str,
+        model_id: str,
+        provider: str,
+    ):
+        """
+        Initialize the BaseEndpoint.
+
+        Args:
+            endpoint_name (str): The name of the endpoint.
+            model_id (str): The identifier of the model associated with this endpoint.
+            provider (str): The provider of the endpoint.
+
+        Returns:
+            None
+        """
+        self.endpoint_name = endpoint_name
+        self.model_id = model_id
+        self.provider = provider
+
+    @abstractmethod
+    def invoke(self, payload: Dict) -> InvocationResponse:
+        """
+        Invoke the endpoint with the given payload.
+
+        This method must be implemented by subclasses to define how the endpoint
+        is invoked and how the response is processed.
+
+        Args:
+            payload (Dict): The input payload for the model.
+
+        Returns:
+            InvocationResponse: An object containing the model's response and associated metrics.
+
+        Raises:
+            NotImplementedError: If the method is not implemented by a subclass.
+        """
+        raise NotImplementedError
+
+    @staticmethod
+    def create_payload(*args, **kwargs):
+        """
+        Create a payload for the endpoint invocation.
+
+        This static method should be implemented by subclasses to define
+        how the payload is created based on the given arguments.
+
+        Args:
+            *args: Variable length argument list.
+            **kwargs: Arbitrary keyword arguments.
+
+        Returns:
+            NotImplemented: This method returns NotImplemented in the base class.
+        """
+        return NotImplemented
+
+    @classmethod
+    def __subclasshook__(cls, C):
+        """
+        Determine if a class is considered a subclass of BaseEndpoint.
+
+        This method is used to implement a custom subclass check. A class
+        is considered a subclass of BaseEndpoint if it has an 'invoke' method.
+
+        Args:
+            C: The class to check.
+
+        Returns:
+            bool or NotImplemented: True if the class is a subclass, False if it isn't,
+                                    or NotImplemented if the check is inconclusive.
+        """
+        if cls is Endpoint:
+            if any("invoke" in B.__dict__ for B in C.__mro__):
+                return True
+        return NotImplemented
+
+    def save(self, output_path: os.PathLike) -> os.PathLike:
+        """
+        Save the endpoint configuration to a JSON file.
+
+        This method serializes the endpoint's configuration (excluding private attributes)
+        to a JSON file at the specified path.
+
+        Args:
+            output_path (str | UPath): The path where the configuration file will be saved.
+
+        Returns:
+            None
+        """
+        output_path = Path(output_path)
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+        with output_path.open("w") as f:
+            endpoint_conf = self.to_dict()
+            json.dump(endpoint_conf, f, indent=4, default=str)
+        return output_path
+
+    def to_dict(self) -> Dict:
+        """
+        Convert the endpoint configuration to a dictionary.
+
+        Returns:
+            Dict: A dictionary representation of the endpoint configuration.
+        """
+        endpoint_conf = {k: v for k, v in vars(self).items() if not k.startswith("_")}
+        endpoint_conf["endpoint_type"] = self.__class__.__name__
+        return endpoint_conf
+
+    @classmethod
+    def load_from_file(cls, input_path: os.PathLike) -> Self:
+        """
+        Load an endpoint configuration from a JSON file.
+
+        This class method reads a JSON file containing an endpoint configuration,
+        determines the appropriate endpoint class, and instantiates it with the
+        loaded configuration.
+
+        Args:
+            input_path (str|UPath): The path to the JSON configuration file.
+
+        Returns:
+            Endpoint: An instance of the appropriate endpoint class, initialized
+                      with the configuration from the file.
+        """
+
+        input_path = Path(input_path)
+        with input_path.open("r") as f:
+            data = json.load(f)
+        endpoint_type = data.pop("endpoint_type")
+        endpoint_module = importlib.import_module("llmeter.endpoints")
+        endpoint_class = getattr(endpoint_module, endpoint_type)
+        return endpoint_class(**data)
+
+    @classmethod
+    def load(cls, endpoint_config: Dict) -> Self:  # type: ignore
+        """
+        Load an endpoint configuration from a dictionary.
+
+        This class method reads a dictionary containing an endpoint configuration,
+        determines the appropriate endpoint class, and instantiates it with the
+        loaded configuration.
+
+        Args:
+            data (Dict): A dictionary containing the endpoint configuration.
+
+        Returns:
+            Endpoint: An instance of the appropriate endpoint class, initialized
+                      with the configuration from the dictionary.
+        """
+        endpoint_type = endpoint_config.pop("endpoint_type")
+        endpoint_module = importlib.import_module("llmeter.endpoints")
+        endpoint_class = getattr(endpoint_module, endpoint_type)
+        return endpoint_class(**endpoint_config)