-
Notifications
You must be signed in to change notification settings - Fork 9
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #3 from triton-inference-server/fpetrini-migrate-p…
…a-history Migrate PA History
- Loading branch information
Showing
202 changed files
with
33,670 additions
and
3,785 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,171 @@ | ||
| <!-- | ||
| Copyright (c) 2020-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | ||
| Redistribution and use in source and binary forms, with or without | ||
| modification, are permitted provided that the following conditions | ||
| are met: | ||
| * Redistributions of source code must retain the above copyright | ||
| notice, this list of conditions and the following disclaimer. | ||
| * Redistributions in binary form must reproduce the above copyright | ||
| notice, this list of conditions and the following disclaimer in the | ||
| documentation and/or other materials provided with the distribution. | ||
| * Neither the name of NVIDIA CORPORATION nor the names of its | ||
| contributors may be used to endorse or promote products derived | ||
| from this software without specific prior written permission. | ||
| THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY | ||
| EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE | ||
| IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR | ||
| PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR | ||
| CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, | ||
| EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, | ||
| PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | ||
| PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY | ||
| OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | ||
| (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE | ||
| OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | ||
| --> | ||
|
|
||
| # Triton Performance Analyzer | ||
|
|
||
| Triton Performance Analyzer is CLI tool which can help you optimize the | ||
| inference performance of models running on Triton Inference Server by measuring | ||
| changes in performance as you experiment with different optimization strategies. | ||
|
|
||
| <br> | ||
|
|
||
| # Features | ||
|
|
||
| ### Inference Load Modes | ||
|
|
||
| - [Concurrency Mode](docs/inference_load_modes.md#concurrency-mode) simlulates | ||
| load by maintaining a specific concurrency of outgoing requests to the | ||
| server | ||
|
|
||
| - [Request Rate Mode](docs/inference_load_modes.md#request-rate-mode) simulates | ||
| load by sending consecutive requests at a specific rate to the server | ||
|
|
||
| - [Custom Interval Mode](docs/inference_load_modes.md#custom-interval-mode) | ||
| simulates load by sending consecutive requests at specific intervals to the | ||
| server | ||
|
|
||
| ### Performance Measurement Modes | ||
|
|
||
| - [Time Windows Mode](docs/measurements_metrics.md#time-windows) measures model | ||
| performance repeatedly over a specific time interval until performance has | ||
| stabilized | ||
|
|
||
| - [Count Windows Mode](docs/measurements_metrics.md#count-windows) measures | ||
| model performance repeatedly over a specific number of requests until | ||
| performance has stabilized | ||
|
|
||
| ### Other Features | ||
|
|
||
| - [Sequence Models](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/architecture.md#stateful-models), | ||
| [Ensemble Models](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/architecture.md#ensemble-models), | ||
| and | ||
| [Decoupled Models](https://github.com/triton-inference-server/server/blob/main/docs/user_guide/decoupled_models.md) | ||
| can be profiled in addition to standard/stateless/coupled models | ||
|
|
||
| - [Input Data](docs/input_data.md) to model inferences can be auto-generated or | ||
| specified as well as verifying output | ||
|
|
||
| - [TensorFlow Serving](docs/benchmarking.md#benchmarking-tensorflow-serving) and | ||
| [TorchServe](docs/benchmarking.md#benchmarking-torchserve) can be used as the | ||
| inference server in addition to the default Triton server | ||
|
|
||
| <br> | ||
|
|
||
| # Quick Start | ||
|
|
||
| The steps below will guide you on how to start using Perf Analyzer. | ||
|
|
||
| ### Step 1: Start Triton Container | ||
|
|
||
| ```bash | ||
| export RELEASE=<yy.mm> # e.g. to use the release from the end of February of 2023, do `export RELEASE=23.02` | ||
|
|
||
| docker pull nvcr.io/nvidia/tritonserver:${RELEASE}-py3 | ||
|
|
||
| docker run --gpus all --rm -it --net host nvcr.io/nvidia/tritonserver:${RELEASE}-py3 | ||
| ``` | ||
|
|
||
| ### Step 2: Download `simple` Model | ||
|
|
||
| ```bash | ||
| # inside triton container | ||
| git clone --depth 1 https://github.com/triton-inference-server/server | ||
|
|
||
| mkdir model_repository ; cp -r server/docs/examples/model_repository/simple model_repository | ||
| ``` | ||
|
|
||
| ### Step 3: Start Triton Server | ||
|
|
||
| ```bash | ||
| # inside triton container | ||
| tritonserver --model-repository $(pwd)/model_repository &> server.log & | ||
|
|
||
| # confirm server is ready, look for 'HTTP/1.1 200 OK' | ||
| curl -v localhost:8000/v2/health/ready | ||
|
|
||
| # detach (CTRL-p CTRL-q) | ||
| ``` | ||
|
|
||
| ### Step 4: Start Triton SDK Container | ||
|
|
||
| ```bash | ||
| docker pull nvcr.io/nvidia/tritonserver:${RELEASE}-py3-sdk | ||
|
|
||
| docker run --gpus all --rm -it --net host nvcr.io/nvidia/tritonserver:${RELEASE}-py3-sdk | ||
| ``` | ||
|
|
||
| ### Step 5: Run Perf Analyzer | ||
|
|
||
| ```bash | ||
| # inside sdk container | ||
| perf_analyzer -m simple | ||
| ``` | ||
|
|
||
| See the full [quick start guide](docs/quick_start.md) for additional tips on | ||
| how to analyze output. | ||
|
|
||
| <br> | ||
|
|
||
| # Documentation | ||
|
|
||
| - [Installation](docs/install.md) | ||
| - [Perf Analyzer CLI](docs/cli.md) | ||
| - [Inference Load Modes](docs/inference_load_modes.md) | ||
| - [Input Data](docs/input_data.md) | ||
| - [Measurements & Metrics](docs/measurements_metrics.md) | ||
| - [Benchmarking](docs/benchmarking.md) | ||
|
|
||
| <br> | ||
|
|
||
| # Contributing | ||
|
|
||
| Contributions to Triton Perf Analyzer are more than welcome. To contribute | ||
| please review the [contribution | ||
| guidelines](https://github.com/triton-inference-server/server/blob/main/CONTRIBUTING.md), | ||
| then fork and create a pull request. | ||
|
|
||
| <br> | ||
|
|
||
| # Reporting problems, asking questions | ||
|
|
||
| We appreciate any feedback, questions or bug reporting regarding this | ||
| project. When help with code is needed, follow the process outlined in | ||
| the Stack Overflow (https://stackoverflow.com/help/mcve) | ||
| document. Ensure posted examples are: | ||
|
|
||
| - minimal - use as little code as possible that still produces the | ||
| same problem | ||
|
|
||
| - complete - provide all parts needed to reproduce the problem. Check | ||
| if you can strip external dependency and still show the problem. The | ||
| less time we spend on reproducing problems the more time we have to | ||
| fix it | ||
|
|
||
| - verifiable - test the code you're about to provide to make sure it | ||
| reproduces the problem. Remove all other problems that are not | ||
| related to your request/question. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,67 @@ | ||
| // Copyright 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. | ||
| // | ||
| // Redistribution and use in source and binary forms, with or without | ||
| // modification, are permitted provided that the following conditions | ||
| // are met: | ||
| // * Redistributions of source code must retain the above copyright | ||
| // notice, this list of conditions and the following disclaimer. | ||
| // * Redistributions in binary form must reproduce the above copyright | ||
| // notice, this list of conditions and the following disclaimer in the | ||
| // documentation and/or other materials provided with the distribution. | ||
| // * Neither the name of NVIDIA CORPORATION nor the names of its | ||
| // contributors may be used to endorse or promote products derived | ||
| // from this software without specific prior written permission. | ||
| // | ||
| // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY | ||
| // EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE | ||
| // IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR | ||
| // PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR | ||
| // CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, | ||
| // EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, | ||
| // PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR | ||
| // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY | ||
| // OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | ||
| // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE | ||
| // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | ||
| #pragma once | ||
|
|
||
| #include <queue> | ||
|
|
||
| #include "ictx_id_tracker.h" | ||
|
|
||
| namespace triton { namespace perfanalyzer { | ||
|
|
||
| // Base class for CtxIdTrackers that track available IDs via a queue | ||
| // | ||
| class BaseQueueCtxIdTracker : public ICtxIdTracker { | ||
| public: | ||
| BaseQueueCtxIdTracker() = default; | ||
|
|
||
| void Restore(size_t id) override { free_ctx_ids_.push(id); } | ||
|
|
||
| size_t Get() override | ||
| { | ||
| if (!IsAvailable()) { | ||
| throw std::runtime_error("free ctx id list is empty"); | ||
| } | ||
|
|
||
| size_t ctx_id = free_ctx_ids_.front(); | ||
| free_ctx_ids_.pop(); | ||
| return ctx_id; | ||
| } | ||
|
|
||
| bool IsAvailable() override { return free_ctx_ids_.size() > 0; } | ||
|
|
||
| protected: | ||
| std::queue<size_t> free_ctx_ids_; | ||
|
|
||
| // Erase all entries in the tracking queue | ||
| // | ||
| void Clear() | ||
| { | ||
| std::queue<size_t> empty; | ||
| std::swap(free_ctx_ids_, empty); | ||
| } | ||
| }; | ||
|
|
||
| }}; // namespace triton::perfanalyzer |
Oops, something went wrong.