mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
527 lines
56 KiB
HTML
527 lines
56 KiB
HTML
|
|
|
|
<!DOCTYPE html>
|
|
<html class="writer-html5" lang="en" data-content_root="../../../">
|
|
<head>
|
|
<meta charset="utf-8" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<title>tensorrt_llm.runtime.session — tensorrt_llm documentation</title>
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=80d5e7a1" />
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/css/theme.css?v=e59714d7" />
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css?v=76b2166b" />
|
|
|
|
|
|
<script src="../../../_static/jquery.js?v=5d32c60e"></script>
|
|
<script src="../../../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
|
|
<script src="../../../_static/documentation_options.js?v=5929fcd5"></script>
|
|
<script src="../../../_static/doctools.js?v=888ff710"></script>
|
|
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
|
<script src="../../../_static/clipboard.min.js?v=a7894cd8"></script>
|
|
<script src="../../../_static/copybutton.js?v=65e89d2a"></script>
|
|
<script src="../../../_static/js/theme.js"></script>
|
|
<link rel="index" title="Index" href="../../../genindex.html" />
|
|
<link rel="search" title="Search" href="../../../search.html" />
|
|
</head>
|
|
|
|
<body class="wy-body-for-nav">
|
|
<div class="wy-grid-for-nav">
|
|
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
|
<div class="wy-side-scroll">
|
|
<div class="wy-side-nav-search" >
|
|
|
|
|
|
|
|
<a href="../../../index.html" class="icon icon-home">
|
|
tensorrt_llm
|
|
</a>
|
|
<div role="search">
|
|
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
|
|
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
|
|
<input type="hidden" name="check_keywords" value="yes" />
|
|
<input type="hidden" name="area" value="default" />
|
|
</form>
|
|
</div>
|
|
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
|
|
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../overview.html">Overview</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../quick-start-guide.html">Quick Start Guide</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../key-features.html">Key Features</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../release-notes.html">Release Notes</a></li>
|
|
</ul>
|
|
<p class="caption" role="heading"><span class="caption-text">Installation</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../installation/linux.html">Installing on Linux</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../installation/build-from-source-linux.html">Building from Source Code on Linux</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../installation/windows.html">Installing on Windows</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../installation/build-from-source-windows.html">Building from Source Code on Windows</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../installation/grace-hopper.html">Installing on Grace Hopper</a></li>
|
|
</ul>
|
|
<p class="caption" role="heading"><span class="caption-text">LLM API</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/index.html">API Introduction</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/reference.html">API Reference</a></li>
|
|
</ul>
|
|
<p class="caption" role="heading"><span class="caption-text">LLM API Examples</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api-examples/index.html">LLM Examples Introduction</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api-examples/customization.html">Common Customizations</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api-examples/llm_api_examples.html">Examples</a></li>
|
|
</ul>
|
|
<p class="caption" role="heading"><span class="caption-text">Model Definition API</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.layers.html">Layers</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.functional.html">Functionals</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.models.html">Models</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.plugin.html">Plugin</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.quantization.html">Quantization</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../python-api/tensorrt_llm.runtime.html">Runtime</a></li>
|
|
</ul>
|
|
<p class="caption" role="heading"><span class="caption-text">C++ API</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/executor.html">Executor</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/runtime.html">Runtime</a></li>
|
|
</ul>
|
|
<p class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-build.html">trtllm-build</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-serve.html">trtllm-serve</a></li>
|
|
</ul>
|
|
<p class="caption" role="heading"><span class="caption-text">Architecture</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/overview.html">TensorRT-LLM Architecture</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/core-concepts.html">Model Definition</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/core-concepts.html#compilation">Compilation</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/core-concepts.html#runtime">Runtime</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/core-concepts.html#multi-gpu-and-multi-node-support">Multi-GPU and Multi-Node Support</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/checkpoint.html">TensorRT-LLM Checkpoint</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/workflow.html">TensorRT-LLM Build Workflow</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../architecture/add-model.html">Adding a Model</a></li>
|
|
</ul>
|
|
<p class="caption" role="heading"><span class="caption-text">Advanced</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/gpt-attention.html">Multi-Head, Multi-Query, and Group-Query Attention</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/gpt-runtime.html">C++ GPT Runtime</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/executor.html">Executor API</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/graph-rewriting.html">Graph Rewriting Module</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/inference-request.html">Inference Request</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/inference-request.html#responses">Responses</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/lora.html">Run gpt-2b + LoRA using GptManager / cpp runtime</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/expert-parallelism.html">Expert Parallelism in TensorRT-LLM</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/kv-cache-reuse.html">KV cache reuse</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/speculative-decoding.html">Speculative Sampling</a></li>
|
|
</ul>
|
|
<p class="caption" role="heading"><span class="caption-text">Performance</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-overview.html">Overview</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-benchmarking.html">Benchmarking</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-best-practices.html">Best Practices</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../performance/perf-analysis.html">Performance Analysis</a></li>
|
|
</ul>
|
|
<p class="caption" role="heading"><span class="caption-text">Reference</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../reference/troubleshooting.html">Troubleshooting</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../reference/support-matrix.html">Support Matrix</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../reference/precision.html">Numerical Precision</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../reference/memory.html">Memory Usage of TensorRT-LLM</a></li>
|
|
</ul>
|
|
<p class="caption" role="heading"><span class="caption-text">Blogs</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/H100vsA100.html">H100 has 4.6x A100 Performance in TensorRT-LLM, achieving 10,000 tok/s at 100ms to first token</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/H200launch.html">H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/Falcon180B-H200.html">Falcon-180B on a single H200 GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/quantization-in-TRT-LLM.html">Speed up inference with SOTA quantization techniques in TRT-LLM</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../blogs/XQA-kernel.html">New XQA-kernel provides 2.4x more Llama-70B throughput within the same latency budget</a></li>
|
|
</ul>
|
|
|
|
</div>
|
|
</div>
|
|
</nav>
|
|
|
|
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
|
|
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
|
<a href="../../../index.html">tensorrt_llm</a>
|
|
</nav>
|
|
|
|
<div class="wy-nav-content">
|
|
<div class="rst-content">
|
|
<div role="navigation" aria-label="Page navigation">
|
|
<ul class="wy-breadcrumbs">
|
|
<li><a href="../../../index.html" class="icon icon-home" aria-label="Home"></a></li>
|
|
<li class="breadcrumb-item"><a href="../../index.html">Module code</a></li>
|
|
<li class="breadcrumb-item active">tensorrt_llm.runtime.session</li>
|
|
<li class="wy-breadcrumbs-aside">
|
|
</li>
|
|
</ul>
|
|
<hr/>
|
|
</div>
|
|
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
|
<div itemprop="articleBody">
|
|
|
|
<h1>Source code for tensorrt_llm.runtime.session</h1><div class="highlight"><pre>
|
|
<span></span><span class="c1"># SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.</span>
|
|
<span class="c1"># SPDX-License-Identifier: Apache-2.0</span>
|
|
<span class="c1">#</span>
|
|
<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
|
|
<span class="c1"># you may not use this file except in compliance with the License.</span>
|
|
<span class="c1"># You may obtain a copy of the License at</span>
|
|
<span class="c1">#</span>
|
|
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
|
|
<span class="c1">#</span>
|
|
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
|
|
<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
|
|
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
|
|
<span class="c1"># See the License for the specific language governing permissions and</span>
|
|
<span class="c1"># limitations under the License.</span>
|
|
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">annotations</span>
|
|
|
|
<span class="kn">import</span> <span class="nn">contextlib</span>
|
|
<span class="kn">from</span> <span class="nn">dataclasses</span> <span class="kn">import</span> <span class="n">dataclass</span>
|
|
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Optional</span>
|
|
|
|
<span class="c1"># isort: off</span>
|
|
<span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="kn">import</span> <span class="nn">tensorrt</span> <span class="k">as</span> <span class="nn">trt</span>
|
|
<span class="c1"># isort: on</span>
|
|
|
|
<span class="kn">from</span> <span class="nn">.._utils</span> <span class="kn">import</span> <span class="n">torch_dtype_to_trt</span><span class="p">,</span> <span class="n">trt_dtype_to_torch</span>
|
|
<span class="kn">from</span> <span class="nn">..logger</span> <span class="kn">import</span> <span class="n">logger</span>
|
|
|
|
|
|
<span class="nd">@contextlib</span><span class="o">.</span><span class="n">contextmanager</span>
|
|
<span class="k">def</span> <span class="nf">_scoped_stream</span><span class="p">():</span>
|
|
<span class="w"> </span><span class="sd">'''Create a scoped cuda stream, and synchronize it when the context is destroyed</span>
|
|
<span class="sd"> '''</span>
|
|
<span class="c1">#TODO: delete torch, use cuda native python bindings</span>
|
|
<span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="n">stream</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">current_stream</span><span class="p">()</span>
|
|
<span class="k">try</span><span class="p">:</span>
|
|
<span class="c1"># return a handle, trt and other lib does not recognize torch.cuda.Stream</span>
|
|
<span class="k">yield</span> <span class="n">stream</span><span class="o">.</span><span class="n">cuda_stream</span>
|
|
<span class="k">finally</span><span class="p">:</span>
|
|
<span class="n">stream</span><span class="o">.</span><span class="n">synchronize</span><span class="p">()</span>
|
|
|
|
|
|
<div class="viewcode-block" id="TensorInfo">
|
|
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.TensorInfo">[docs]</a>
|
|
<span class="nd">@dataclass</span>
|
|
<span class="k">class</span> <span class="nc">TensorInfo</span><span class="p">:</span>
|
|
<span class="n">name</span><span class="p">:</span> <span class="nb">str</span>
|
|
<span class="n">dtype</span><span class="p">:</span> <span class="n">trt</span><span class="o">.</span><span class="n">DataType</span>
|
|
<span class="n">shape</span><span class="p">:</span> <span class="nb">tuple</span></div>
|
|
|
|
<span class="c1"># add more info like strides, formats if needed</span>
|
|
|
|
|
|
<div class="viewcode-block" id="Session">
|
|
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session">[docs]</a>
|
|
<span class="k">class</span> <span class="nc">Session</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">''' Session is a managed TensorRT runtime. '''</span>
|
|
|
|
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
|
<span class="c1"># use Session.from_serialized_engine to create a session</span>
|
|
<span class="k">pass</span>
|
|
|
|
<span class="k">def</span> <span class="nf">_init</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">engine_buffer</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">'''</span>
|
|
<span class="sd"> @brief: Setup TensorRT engines and context from a serialized engine file</span>
|
|
<span class="sd"> @param engine_buffer: a buffer holds the serialized TRT engine</span>
|
|
<span class="sd"> '''</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">_runtime</span> <span class="o">=</span> <span class="n">trt</span><span class="o">.</span><span class="n">Runtime</span><span class="p">(</span><span class="n">logger</span><span class="o">.</span><span class="n">trt_logger</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">engine_buffer</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">_engine</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">runtime</span><span class="o">.</span><span class="n">deserialize_cuda_engine</span><span class="p">(</span><span class="n">engine_buffer</span><span class="p">)</span>
|
|
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">_context</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">streamable_weights_size</span><span class="p">:</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">__prepare_execution_contexts</span><span class="p">()</span>
|
|
<span class="k">return</span> <span class="bp">self</span>
|
|
|
|
<span class="k">def</span> <span class="nf">__prepare_execution_contexts</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">_context</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">create_execution_context</span><span class="p">()</span>
|
|
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_context</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">,</span> <span class="s2">"Failed to create an execution context!"</span>
|
|
<span class="k">with</span> <span class="n">_scoped_stream</span><span class="p">()</span> <span class="k">as</span> <span class="n">stream</span><span class="p">:</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">_context</span><span class="o">.</span><span class="n">set_optimization_profile_async</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">stream</span><span class="p">)</span>
|
|
|
|
<div class="viewcode-block" id="Session.from_serialized_engine">
|
|
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session.from_serialized_engine">[docs]</a>
|
|
<span class="nd">@staticmethod</span>
|
|
<span class="k">def</span> <span class="nf">from_serialized_engine</span><span class="p">(</span><span class="n">engine</span><span class="p">)</span> <span class="o">-></span> <span class="n">Session</span><span class="p">:</span>
|
|
<span class="w"> </span><span class="sd">'''</span>
|
|
<span class="sd"> @brief: Create a session from a serialized engine</span>
|
|
<span class="sd"> @param engine: a serialized engine</span>
|
|
<span class="sd"> @return: a Session object</span>
|
|
<span class="sd"> '''</span>
|
|
<span class="n">session</span> <span class="o">=</span> <span class="n">Session</span><span class="p">()</span>
|
|
<span class="k">return</span> <span class="n">session</span><span class="o">.</span><span class="n">_init</span><span class="p">(</span><span class="n">engine</span><span class="p">)</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="Session.from_engine">
|
|
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session.from_engine">[docs]</a>
|
|
<span class="nd">@staticmethod</span>
|
|
<span class="k">def</span> <span class="nf">from_engine</span><span class="p">(</span><span class="n">engine</span><span class="p">)</span> <span class="o">-></span> <span class="n">Session</span><span class="p">:</span>
|
|
<span class="w"> </span><span class="sd">'''</span>
|
|
<span class="sd"> @brief: Create a session from an existing ICudaEngine engine</span>
|
|
<span class="sd"> @param engine: an ICudaEngine</span>
|
|
<span class="sd"> @return: a Session object</span>
|
|
<span class="sd"> '''</span>
|
|
<span class="n">session</span> <span class="o">=</span> <span class="n">Session</span><span class="p">()</span>
|
|
<span class="n">session</span><span class="o">.</span><span class="n">engine</span> <span class="o">=</span> <span class="n">engine</span>
|
|
<span class="k">return</span> <span class="n">session</span><span class="o">.</span><span class="n">_init</span><span class="p">()</span></div>
|
|
|
|
|
|
<span class="nd">@property</span>
|
|
<span class="k">def</span> <span class="nf">runtime</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">trt</span><span class="o">.</span><span class="n">Runtime</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_runtime</span>
|
|
|
|
<span class="nd">@property</span>
|
|
<span class="k">def</span> <span class="nf">engine</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">trt</span><span class="o">.</span><span class="n">ICudaEngine</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_engine</span>
|
|
|
|
<span class="nd">@engine</span><span class="o">.</span><span class="n">setter</span>
|
|
<span class="k">def</span> <span class="nf">engine</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">engine</span><span class="p">:</span> <span class="n">trt</span><span class="o">.</span><span class="n">ICudaEngine</span><span class="p">):</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">_engine</span> <span class="o">=</span> <span class="n">engine</span>
|
|
|
|
<span class="nd">@property</span>
|
|
<span class="k">def</span> <span class="nf">context</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">trt</span><span class="o">.</span><span class="n">IExecutionContext</span><span class="p">:</span>
|
|
<span class="w"> </span><span class="sd">'''</span>
|
|
<span class="sd"> @brief: Get the default TensorRT execution context,</span>
|
|
<span class="sd"> use self.engine.create_execution_context() to create a new context if needed</span>
|
|
<span class="sd"> @return: one TensorRT execution context object</span>
|
|
<span class="sd"> '''</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_context</span>
|
|
|
|
<span class="nd">@property</span>
|
|
<span class="k">def</span> <span class="nf">context_mem_size</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">device_memory_size_v2</span>
|
|
|
|
<span class="k">def</span> <span class="nf">_print_engine_info</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">'''print engine info for debug purpose, internal use only.</span>
|
|
<span class="sd"> '''</span>
|
|
<span class="n">refittable</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">refittable</span>
|
|
<span class="n">num_layers</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_layers</span>
|
|
<span class="n">device_memory_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">device_memory_size_v2</span>
|
|
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">name</span>
|
|
<span class="n">nb_profiles</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_optimization_profiles</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
|
|
<span class="sa">f</span><span class="s2">"Engine:</span><span class="si">{</span><span class="n">name</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">refittable</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">num_layers</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">device_memory_size</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">nb_profiles</span><span class="si">=:}</span><span class="s2">"</span>
|
|
<span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">_print_io_info</span><span class="p">()</span>
|
|
|
|
<span class="k">def</span> <span class="nf">_print_io_info</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">'''print engine i/o info for debug purpose, internal use only.</span>
|
|
<span class="sd"> '''</span>
|
|
|
|
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_io_tensors</span><span class="p">):</span>
|
|
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_name</span><span class="p">(</span><span class="n">i</span><span class="p">)</span>
|
|
<span class="n">mode</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_mode</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
|
|
<span class="n">shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_shape</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
|
|
<span class="n">dtype</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_dtype</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
|
|
<span class="n">tformat</span> <span class="o">=</span> <span class="s2">";"</span><span class="o">.</span><span class="n">join</span><span class="p">([</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_format_desc</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">p</span><span class="p">)</span>
|
|
<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_optimization_profiles</span><span class="p">)</span>
|
|
<span class="p">])</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
|
|
<span class="sa">f</span><span class="s2">"Tensor:</span><span class="si">{</span><span class="n">name</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">mode</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">shape</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">dtype</span><span class="si">=:}</span><span class="s2">, </span><span class="si">{</span><span class="n">tformat</span><span class="si">=:}</span><span class="s2">"</span><span class="p">)</span>
|
|
|
|
<div class="viewcode-block" id="Session.set_shapes">
|
|
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session.set_shapes">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">set_shapes</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
|
|
<span class="n">tensor_dict</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">],</span>
|
|
<span class="n">context</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">trt</span><span class="o">.</span><span class="n">IExecutionContext</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="n">context</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">context</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">context</span>
|
|
|
|
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_io_tensors</span><span class="p">):</span>
|
|
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_name</span><span class="p">(</span><span class="n">i</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_mode</span><span class="p">(</span><span class="n">name</span><span class="p">)</span> <span class="o">==</span> <span class="n">trt</span><span class="o">.</span><span class="n">TensorIOMode</span><span class="o">.</span><span class="n">INPUT</span><span class="p">:</span>
|
|
<span class="n">ok</span> <span class="o">=</span> <span class="n">context</span><span class="o">.</span><span class="n">set_input_shape</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">tensor_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span>
|
|
<span class="sa">f</span><span class="s2">"setting input tensor </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> with shape </span><span class="si">{</span><span class="n">tensor_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2">"</span>
|
|
<span class="p">)</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">ok</span><span class="p">:</span>
|
|
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
|
|
<span class="sa">f</span><span class="s2">"Couldn't assign </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> with shape </span><span class="si">{</span><span class="n">tensor_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2">, "</span>
|
|
<span class="sa">f</span><span class="s2">"engine supports [min, opt, max] = </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_profile_shape</span><span class="p">(</span><span class="n">name</span><span class="p">,</span><span class="w"> </span><span class="n">context</span><span class="o">.</span><span class="n">active_optimization_profile</span><span class="p">)</span><span class="si">}</span><span class="s2">"</span>
|
|
<span class="p">)</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="Session.infer_shapes">
|
|
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session.infer_shapes">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">infer_shapes</span><span class="p">(</span>
|
|
<span class="bp">self</span><span class="p">,</span>
|
|
<span class="n">inputs</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">TensorInfo</span><span class="p">],</span>
|
|
<span class="n">context</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">trt</span><span class="o">.</span><span class="n">IExecutionContext</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="p">)</span> <span class="o">-></span> <span class="n">List</span><span class="p">[</span><span class="n">TensorInfo</span><span class="p">]:</span>
|
|
<span class="w"> </span><span class="sd">'''</span>
|
|
<span class="sd"> @brief: Set input shapes to given context, and infer the output shapes from the given input shapes.</span>
|
|
<span class="sd"> This function should be called every time when the input shapes are changed before calling run().</span>
|
|
<span class="sd"> Or call the context.set_input_shape on all dynamic shaped input tensors manually.</span>
|
|
<span class="sd"> @param inputs: list of TensorInfo object, each item represents an input tensor</span>
|
|
<span class="sd"> @param context: TensorRT execution context, if None, use the default context</span>
|
|
<span class="sd"> @return: list of TensorInfo object, each item represents an output tensor, returns None if failed</span>
|
|
<span class="sd"> '''</span>
|
|
<span class="c1"># set shape to the default context if context is not specified</span>
|
|
<span class="k">if</span> <span class="n">context</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">context</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">context</span>
|
|
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">inputs</span><span class="p">:</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_mode</span><span class="p">(</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="p">)</span> <span class="o">!=</span> <span class="n">trt</span><span class="o">.</span><span class="n">TensorIOMode</span><span class="o">.</span><span class="n">INPUT</span><span class="p">:</span>
|
|
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Tensor:</span><span class="si">{</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="si">}</span><span class="s2"> is not an input tensor"</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_dtype</span><span class="p">(</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="p">)</span> <span class="o">!=</span> <span class="n">i</span><span class="o">.</span><span class="n">dtype</span><span class="p">:</span>
|
|
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Tensor:</span><span class="si">{</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="si">}</span><span class="s2"> has wrong dtype"</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">context</span><span class="o">.</span><span class="n">set_input_shape</span><span class="p">(</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">i</span><span class="o">.</span><span class="n">shape</span><span class="p">):</span>
|
|
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span>
|
|
<span class="sa">f</span><span class="s2">"Could not set shape </span><span class="si">{</span><span class="n">i</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2"> for tensor </span><span class="si">{</span><span class="n">i</span><span class="o">.</span><span class="n">name</span><span class="si">}</span><span class="s2">. Please check the profile range for which your model was build."</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="n">outputs</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">num_io_tensors</span><span class="p">):</span>
|
|
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_name</span><span class="p">(</span><span class="n">i</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_mode</span><span class="p">(</span><span class="n">name</span><span class="p">)</span> <span class="o">==</span> <span class="n">trt</span><span class="o">.</span><span class="n">TensorIOMode</span><span class="o">.</span><span class="n">OUTPUT</span><span class="p">:</span>
|
|
<span class="n">shape</span> <span class="o">=</span> <span class="n">context</span><span class="o">.</span><span class="n">get_tensor_shape</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
|
|
<span class="n">dtype</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">get_tensor_dtype</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
|
|
<span class="n">outputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">TensorInfo</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">dtype</span><span class="p">,</span> <span class="n">shape</span><span class="p">))</span>
|
|
<span class="k">return</span> <span class="n">outputs</span></div>
|
|
|
|
|
|
<span class="k">def</span> <span class="nf">_set_weight_streaming</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">gpu_weights_percent</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">streamable_weights_size</span><span class="p">:</span>
|
|
<span class="k">assert</span> <span class="n">gpu_weights_percent</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"Engine built without weight streaming. Cannot set gpu_weights_percent to a value other than 1."</span>
|
|
<span class="k">return</span>
|
|
|
|
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
|
|
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">_context</span> <span class="o">=</span> <span class="kc">None</span>
|
|
|
|
<span class="nb">min</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="nb">max</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">streamable_weights_size</span>
|
|
<span class="n">budget</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">gpu_weights_percent</span> <span class="o">*</span> <span class="nb">max</span><span class="p">)</span>
|
|
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">weight_streaming_budget_v2</span> <span class="o">=</span> <span class="n">budget</span>
|
|
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">engine</span><span class="o">.</span><span class="n">weight_streaming_budget_v2</span> <span class="o">==</span> <span class="n">budget</span><span class="p">,</span> <span class="s2">"Failed to set weight streaming budget!"</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
|
|
<span class="sa">f</span><span class="s2">"Set gpu weights percent to </span><span class="si">{</span><span class="n">gpu_weights_percent</span><span class="si">}</span><span class="s2">, which is </span><span class="si">{</span><span class="n">budget</span><span class="si">}</span><span class="s2"> bytes. Valid range: </span><span class="si">{</span><span class="nb">min</span><span class="si">}</span><span class="s2"> bytes ~ </span><span class="si">{</span><span class="nb">max</span><span class="si">}</span><span class="s2"> bytes."</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="k">try</span><span class="p">:</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">__prepare_execution_contexts</span><span class="p">()</span>
|
|
<span class="k">except</span><span class="p">:</span>
|
|
<span class="n">free_mem</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">mem_get_info</span><span class="p">()[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="k">if</span> <span class="n">free_mem</span> <span class="o"><</span> <span class="n">budget</span><span class="p">:</span>
|
|
<span class="k">raise</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">OutOfMemoryError</span><span class="p">(</span>
|
|
<span class="sa">f</span><span class="s2">"Out of Memory: Memory budget is </span><span class="si">{</span><span class="n">budget</span><span class="si">}</span><span class="s2"> bytes but only </span><span class="si">{</span><span class="n">free_mem</span><span class="si">}</span><span class="s2"> bytes are available on the GPU."</span>
|
|
<span class="p">)</span>
|
|
<span class="k">raise</span>
|
|
|
|
<div class="viewcode-block" id="Session.run">
|
|
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.runtime.html#tensorrt_llm.runtime.Session.run">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">run</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
|
|
<span class="n">inputs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">],</span>
|
|
<span class="n">outputs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">],</span>
|
|
<span class="n">stream</span><span class="p">,</span>
|
|
<span class="n">context</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span>
|
|
<span class="w"> </span><span class="sd">'''</span>
|
|
<span class="sd"> @brief: Run the TensorRT engine with the given inputs and outputs</span>
|
|
<span class="sd"> @param inputs: dict of input tensors, key is tensor name, value is tensor pointer or torch tensor</span>
|
|
<span class="sd"> @param outputs: dict of output tensors, key is tensor name, value is tensor pointer or torch tensor</span>
|
|
<span class="sd"> @param stream: cuda stream to enqueue the TensorRT engine on</span>
|
|
<span class="sd"> @param context: TensorRT execution context, if None, use the default context</span>
|
|
<span class="sd"> @return: True if enqueue succeeded, note the enqueue is an async call,</span>
|
|
<span class="sd"> returning True does not mean the execution is finished</span>
|
|
<span class="sd"> '''</span>
|
|
<span class="c1"># enqueue to the default context if context is not specified</span>
|
|
<span class="k">if</span> <span class="n">context</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">context</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">context</span>
|
|
|
|
<span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="k">for</span> <span class="n">tensor_name</span> <span class="ow">in</span> <span class="n">inputs</span><span class="p">:</span>
|
|
<span class="n">tensor</span> <span class="o">=</span> <span class="n">inputs</span><span class="p">[</span><span class="n">tensor_name</span><span class="p">]</span>
|
|
<span class="n">ptr</span> <span class="o">=</span> <span class="n">tensor</span><span class="o">.</span><span class="n">data_ptr</span><span class="p">()</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">tensor</span><span class="p">,</span>
|
|
<span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">)</span> <span class="k">else</span> <span class="n">tensor</span>
|
|
<span class="n">context</span><span class="o">.</span><span class="n">set_tensor_address</span><span class="p">(</span><span class="n">tensor_name</span><span class="p">,</span> <span class="n">ptr</span><span class="p">)</span>
|
|
<span class="k">for</span> <span class="n">tensor_name</span> <span class="ow">in</span> <span class="n">outputs</span><span class="p">:</span>
|
|
<span class="n">tensor</span> <span class="o">=</span> <span class="n">outputs</span><span class="p">[</span><span class="n">tensor_name</span><span class="p">]</span>
|
|
<span class="n">ptr</span> <span class="o">=</span> <span class="n">tensor</span><span class="o">.</span><span class="n">data_ptr</span><span class="p">()</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">tensor</span><span class="p">,</span>
|
|
<span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">)</span> <span class="k">else</span> <span class="n">tensor</span>
|
|
<span class="n">context</span><span class="o">.</span><span class="n">set_tensor_address</span><span class="p">(</span><span class="n">tensor_name</span><span class="p">,</span> <span class="n">ptr</span><span class="p">)</span>
|
|
<span class="n">ok</span> <span class="o">=</span> <span class="n">context</span><span class="o">.</span><span class="n">execute_async_v3</span><span class="p">(</span><span class="n">stream</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">ok</span></div>
|
|
|
|
|
|
<span class="k">def</span> <span class="nf">_debug_run</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
|
|
<span class="n">inputs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="s2">"torch.Tensor"</span><span class="p">],</span>
|
|
<span class="n">context</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="s2">"torch.Tensor"</span><span class="p">]:</span>
|
|
<span class="w"> </span><span class="sd">'''Run the engine enqueue with allocated output tensors, for debug purpose, since it is a sync call and slower than run</span>
|
|
<span class="sd"> '''</span>
|
|
<span class="kn">import</span> <span class="nn">torch</span>
|
|
|
|
<span class="n">inputs_info</span> <span class="o">=</span> <span class="p">[</span>
|
|
<span class="n">TensorInfo</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">torch_dtype_to_trt</span><span class="p">(</span><span class="n">tensor</span><span class="o">.</span><span class="n">dtype</span><span class="p">),</span> <span class="n">tensor</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
|
|
<span class="k">for</span> <span class="n">name</span><span class="p">,</span> <span class="n">tensor</span> <span class="ow">in</span> <span class="n">inputs</span><span class="o">.</span><span class="n">items</span><span class="p">()</span>
|
|
<span class="p">]</span>
|
|
<span class="n">outputs_info</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">infer_shapes</span><span class="p">(</span><span class="n">inputs_info</span><span class="p">)</span>
|
|
<span class="n">outputs</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="n">t</span><span class="o">.</span><span class="n">name</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">empty</span><span class="p">(</span><span class="nb">tuple</span><span class="p">(</span><span class="n">t</span><span class="o">.</span><span class="n">shape</span><span class="p">),</span>
|
|
<span class="n">dtype</span><span class="o">=</span><span class="n">trt_dtype_to_torch</span><span class="p">(</span><span class="n">t</span><span class="o">.</span><span class="n">dtype</span><span class="p">),</span>
|
|
<span class="n">device</span><span class="o">=</span><span class="s1">'cuda'</span><span class="p">)</span>
|
|
<span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">outputs_info</span>
|
|
<span class="p">}</span>
|
|
<span class="k">with</span> <span class="n">_scoped_stream</span><span class="p">()</span> <span class="k">as</span> <span class="n">stream</span><span class="p">:</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">inputs</span><span class="o">=</span><span class="n">inputs</span><span class="p">,</span>
|
|
<span class="n">outputs</span><span class="o">=</span><span class="n">outputs</span><span class="p">,</span>
|
|
<span class="n">stream</span><span class="o">=</span><span class="n">stream</span><span class="p">,</span>
|
|
<span class="n">context</span><span class="o">=</span><span class="n">context</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">outputs</span></div>
|
|
|
|
</pre></div>
|
|
|
|
</div>
|
|
</div>
|
|
<footer>
|
|
|
|
<hr/>
|
|
|
|
<div role="contentinfo">
|
|
<jinja2.runtime.BlockReference object at 0x7f946ada6060>
|
|
|
|
<div class="footer">
|
|
<p>
|
|
Copyright © 2024 NVIDIA Corporation
|
|
</p>
|
|
<p>
|
|
<a class="Link" href="https://www.nvidia.com/en-us/about-nvidia/privacy-policy/" target="_blank" rel="noopener"
|
|
data-cms-ai="0">Privacy Policy</a> |
|
|
<a class="Link" href="https://www.nvidia.com/en-us/about-nvidia/privacy-center/" target="_blank" rel="noopener"
|
|
data-cms-ai="0">Manage My Privacy</a> |
|
|
<a class="Link" href="https://www.nvidia.com/en-us/preferences/start/" target="_blank" rel="noopener"
|
|
data-cms-ai="0">Do Not Sell or Share My Data</a> |
|
|
<a class="Link" href="https://www.nvidia.com/en-us/about-nvidia/terms-of-service/" target="_blank"
|
|
rel="noopener" data-cms-ai="0">Terms of Service</a> |
|
|
<a class="Link" href="https://www.nvidia.com/en-us/about-nvidia/accessibility/" target="_blank" rel="noopener"
|
|
data-cms-ai="0">Accessibility</a> |
|
|
<a class="Link" href="https://www.nvidia.com/en-us/about-nvidia/company-policies/" target="_blank"
|
|
rel="noopener" data-cms-ai="0">Corporate Policies</a> |
|
|
<a class="Link" href="https://www.nvidia.com/en-us/product-security/" target="_blank" rel="noopener"
|
|
data-cms-ai="0">Product Security</a> |
|
|
<a class="Link" href="https://www.nvidia.com/en-us/contact/" target="_blank" rel="noopener"
|
|
data-cms-ai="0">Contact</a>
|
|
</p>
|
|
</div>
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
</footer>
|
|
</div>
|
|
</div>
|
|
</section>
|
|
</div>
|
|
<script>
|
|
jQuery(function () {
|
|
SphinxRtdTheme.Navigation.enable(true);
|
|
});
|
|
</script>
|
|
|
|
</body>
|
|
</html> |