kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
d765533371
TensorRT-LLMs/_modules/tensorrt_llm/layers/mlp.html
石晓伟 d765533371
Update gh-pages (#2276)
2024-09-30 19:28:28 +02:00

599 lines
62 KiB
HTML
Raw Blame History

<!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.layers.mlp &mdash; 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=19f00094" />
<!--[if lt IE 9]>
<script src="../../../_static/js/html5shiv.min.js"></script>
<![endif]-->
<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/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>
</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">LLM API</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../llm-api/index.html">API Reference</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>
</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/graph-rewriting.html">Graph Rewriting Module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../advanced/batch-manager.html">The Batch Manager in TensorRT-LLM</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>
</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-best-practices.html">Best Practices for Tuning the Performance of TensorRT-LLM</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.layers.mlp</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.layers.mlp</h1><div class="highlight"><pre>
<span></span><span class="c1"># SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION &amp; 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 &quot;License&quot;);</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 &quot;AS IS&quot; 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">typing</span> <span class="kn">import</span> <span class="n">Optional</span>
<span class="kn">import</span> <span class="nn">tensorrt</span> <span class="k">as</span> <span class="nn">trt</span>
<span class="kn">from</span> <span class="nn">.._common</span> <span class="kn">import</span> <span class="n">default_net</span>
<span class="kn">from</span> <span class="nn">..functional</span> <span class="kn">import</span> <span class="p">(</span><span class="n">ACT2FN</span><span class="p">,</span> <span class="n">AllReduceFusionParams</span><span class="p">,</span> <span class="n">cast</span><span class="p">,</span> <span class="n">concat</span><span class="p">,</span>
<span class="n">gemm_swiglu</span><span class="p">,</span> <span class="n">is_gated_activation</span><span class="p">)</span>
<span class="kn">from</span> <span class="nn">..module</span> <span class="kn">import</span> <span class="n">Module</span>
<span class="kn">from</span> <span class="nn">..quantization</span> <span class="kn">import</span> <span class="n">QuantMode</span>
<span class="kn">from</span> <span class="nn">..quantization.functional</span> <span class="kn">import</span> <span class="n">quantize</span>
<span class="kn">from</span> <span class="nn">..quantization.layers</span> <span class="kn">import</span> <span class="n">FP8Linear</span><span class="p">,</span> <span class="n">FP8RowLinear</span>
<span class="kn">from</span> <span class="nn">.linear</span> <span class="kn">import</span> <span class="n">ColumnLinear</span><span class="p">,</span> <span class="n">RowLinear</span>
<span class="kn">from</span> <span class="nn">.lora</span> <span class="kn">import</span> <span class="n">LoraRuntimeParams</span>
<span class="kn">from</span> <span class="nn">.normalization</span> <span class="kn">import</span> <span class="n">LayerNorm</span>
<div class="viewcode-block" id="fc_gate_lora">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.fc_gate_lora">[docs]</a>
<span class="k">def</span> <span class="nf">fc_gate_lora</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">lora</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="p">):</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_h_to_4h&quot;</span><span class="p">)</span>
<span class="n">mlp_gate_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_gate&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">mlp_fc_lora_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">mlp_gate_lora_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_in_lora_params</span> <span class="o">=</span> <span class="n">LoraRuntimeParams</span><span class="p">(</span>
<span class="n">lora_ranks</span><span class="o">=</span><span class="p">[</span>
<span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">lora_ranks</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">mlp_gate_lora_params</span><span class="o">.</span><span class="n">lora_ranks</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="p">],</span>
<span class="n">lora_weights_pointers</span><span class="o">=</span><span class="p">[</span>
<span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">lora_weights_pointers</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">mlp_gate_lora_params</span><span class="o">.</span><span class="n">lora_weights_pointers</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="p">],</span>
<span class="n">host_request_types</span><span class="o">=</span><span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">host_request_types</span><span class="p">,</span>
<span class="n">host_context_lengths</span><span class="o">=</span><span class="n">mlp_fc_lora_params</span><span class="o">.</span><span class="n">host_context_lengths</span><span class="p">)</span>
<span class="n">mlp_fc_lora</span><span class="p">,</span> <span class="n">mlp_gate_lora</span> <span class="o">=</span> <span class="n">lora</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">mlp_in_lora_params</span><span class="p">)</span>
<span class="n">mlp_in_result</span> <span class="o">=</span> <span class="n">concat</span><span class="p">([</span><span class="n">mlp_gate_lora</span><span class="p">,</span> <span class="n">mlp_fc_lora</span><span class="p">],</span>
<span class="n">dim</span><span class="o">=</span><span class="n">mlp_fc_lora</span><span class="o">.</span><span class="n">rank</span><span class="p">()</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span>
<span class="k">return</span> <span class="n">mlp_in_result</span>
<span class="k">return</span> <span class="kc">None</span></div>
<div class="viewcode-block" id="MLP">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.MLP">[docs]</a>
<span class="k">class</span> <span class="nc">MLP</span><span class="p">(</span><span class="n">Module</span><span class="p">):</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="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_act</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">quant_mode</span><span class="o">=</span><span class="n">QuantMode</span><span class="p">(</span><span class="mi">0</span><span class="p">),</span>
<span class="n">inner_layernorm</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="mf">1e-05</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="k">if</span> <span class="n">hidden_act</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">ACT2FN</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;unsupported activation function: </span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">hidden_act</span><span class="p">))</span>
<span class="n">fc_output_size</span> <span class="o">=</span> <span class="mi">2</span> <span class="o">*</span> <span class="n">ffn_hidden_size</span> <span class="k">if</span> <span class="n">hidden_act</span> <span class="ow">in</span> <span class="p">[</span>
<span class="s1">&#39;swiglu&#39;</span><span class="p">,</span> <span class="s1">&#39;gegelu&#39;</span>
<span class="p">]</span> <span class="k">else</span> <span class="n">ffn_hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span> <span class="o">=</span> <span class="n">LayerNorm</span><span class="p">(</span><span class="n">ffn_hidden_size</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="n">eps</span><span class="p">)</span> <span class="k">if</span> <span class="n">inner_layernorm</span> <span class="k">else</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fc</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">fc_output_size</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">gather_output</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span> <span class="o">=</span> <span class="n">RowLinear</span><span class="p">(</span><span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_size</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="n">is_expert</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span> <span class="o">=</span> <span class="n">hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ffn_hidden_size</span> <span class="o">=</span> <span class="n">ffn_hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">=</span> <span class="n">hidden_act</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dtype</span> <span class="o">=</span> <span class="n">dtype</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="n">bias</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_group</span> <span class="o">=</span> <span class="n">tp_group</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">=</span> <span class="n">tp_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">quant_mode</span> <span class="o">=</span> <span class="n">quant_mode</span>
<span class="bp">self</span><span class="o">.</span><span class="n">eps</span> <span class="o">=</span> <span class="n">eps</span>
<span class="bp">self</span><span class="o">.</span><span class="n">is_expert</span> <span class="o">=</span> <span class="n">is_expert</span>
<span class="c1"># see optimize_model&#39;s add_lora for LoRA initialization</span>
<span class="bp">self</span><span class="o">.</span><span class="n">lora</span> <span class="o">=</span> <span class="kc">None</span>
<div class="viewcode-block" id="MLP.forward">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.MLP.forward">[docs]</a>
<span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hidden_states</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">gegelu_limit</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="k">if</span> <span class="n">is_gated_activation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">):</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">lora_result</span> <span class="o">=</span> <span class="n">fc_gate_lora</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">lora</span><span class="p">,</span>
<span class="n">lora_layer_params</span><span class="p">)</span>
<span class="k">if</span> <span class="n">lora_result</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">inter</span> <span class="o">+</span> <span class="n">lora_result</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_h_to_4h&quot;</span><span class="p">)</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">mlp_fc_lora_params</span><span class="p">)</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_4h_to_h&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">==</span> <span class="s1">&#39;gegelu&#39;</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">](</span><span class="n">inter</span><span class="p">,</span> <span class="n">gegelu_limit</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">](</span><span class="n">inter</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span><span class="p">(</span><span class="n">inter</span><span class="p">)</span>
<span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">proj</span><span class="p">(</span><span class="n">inter</span><span class="p">,</span> <span class="n">lora_runtime_params</span><span class="o">=</span><span class="n">mlp_proj_lora_params</span><span class="p">)</span>
<span class="k">return</span> <span class="n">output</span></div>
</div>
<div class="viewcode-block" id="GatedMLP">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.GatedMLP">[docs]</a>
<span class="k">class</span> <span class="nc">GatedMLP</span><span class="p">(</span><span class="n">MLP</span><span class="p">):</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="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_act</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">quant_mode</span><span class="o">=</span><span class="n">QuantMode</span><span class="p">(</span><span class="mi">0</span><span class="p">),</span>
<span class="n">inner_layernorm</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="mf">1e-05</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_act</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">quant_mode</span><span class="o">=</span><span class="n">quant_mode</span><span class="p">,</span>
<span class="n">inner_layernorm</span><span class="o">=</span><span class="n">inner_layernorm</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="n">eps</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="n">is_expert</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span> <span class="o">=</span> <span class="n">hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ffn_hidden_size</span> <span class="o">=</span> <span class="n">ffn_hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_group</span> <span class="o">=</span> <span class="n">tp_group</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">=</span> <span class="n">tp_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gate</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">gather_output</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<div class="viewcode-block" id="GatedMLP.forward">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.GatedMLP.forward">[docs]</a>
<span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">hidden_states</span><span class="p">,</span>
<span class="n">lora_layer_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">reduce_fusion_params</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">AllReduceFusionParams</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_h_to_4h&quot;</span><span class="p">)</span>
<span class="n">mlp_gate_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_gate_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_gate&quot;</span><span class="p">)</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_4h_to_h&quot;</span><span class="p">)</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">mlp_fc_lora_params</span><span class="p">)</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">](</span><span class="n">inter</span><span class="p">)</span>
<span class="n">gate</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gate</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">mlp_gate_lora_params</span><span class="p">)</span>
<span class="n">intermediate</span> <span class="o">=</span> <span class="n">inter</span> <span class="o">*</span> <span class="n">gate</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">intermediate</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span><span class="p">(</span><span class="n">intermediate</span><span class="p">)</span>
<span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">proj</span><span class="p">(</span><span class="n">intermediate</span><span class="p">,</span>
<span class="n">lora_runtime_params</span><span class="o">=</span><span class="n">mlp_proj_lora_params</span><span class="p">,</span>
<span class="n">reduce_fusion_params</span><span class="o">=</span><span class="n">reduce_fusion_params</span><span class="p">)</span>
<span class="k">return</span> <span class="n">output</span></div>
</div>
<div class="viewcode-block" id="FusedGatedMLP">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.FusedGatedMLP">[docs]</a>
<span class="k">class</span> <span class="nc">FusedGatedMLP</span><span class="p">(</span><span class="n">Module</span><span class="p">):</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="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_act</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="n">quant_mode</span><span class="o">=</span><span class="n">QuantMode</span><span class="p">(</span><span class="mi">0</span><span class="p">),</span>
<span class="n">inner_layernorm</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="mf">1e-05</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span> <span class="o">=</span> <span class="n">hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ffn_hidden_size</span> <span class="o">=</span> <span class="n">ffn_hidden_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">=</span> <span class="n">hidden_act</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="n">bias</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dtype</span> <span class="o">=</span> <span class="n">dtype</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_group</span> <span class="o">=</span> <span class="n">tp_group</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">=</span> <span class="n">tp_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">quant_mode</span> <span class="o">=</span> <span class="n">quant_mode</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ffn_hidden_size</span> <span class="o">*</span> <span class="mi">2</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bias</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">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">gather_output</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span> <span class="o">=</span> <span class="n">LayerNorm</span><span class="p">(</span><span class="n">ffn_hidden_size</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="n">eps</span><span class="p">)</span> <span class="k">if</span> <span class="n">inner_layernorm</span> <span class="k">else</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span> <span class="o">=</span> <span class="n">RowLinear</span><span class="p">(</span><span class="n">ffn_hidden_size</span><span class="p">,</span>
<span class="n">hidden_size</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="n">bias</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">tp_group</span><span class="p">,</span>
<span class="n">tp_size</span><span class="o">=</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">is_expert</span><span class="o">=</span><span class="n">is_expert</span><span class="p">)</span>
<span class="c1"># see optimize_model&#39;s add_lora for LoRA initialization</span>
<span class="bp">self</span><span class="o">.</span><span class="n">lora</span> <span class="o">=</span> <span class="kc">None</span>
<div class="viewcode-block" id="FusedGatedMLP.fc_gate_plugin">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.FusedGatedMLP.fc_gate_plugin">[docs]</a>
<span class="k">def</span> <span class="nf">fc_gate_plugin</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hidden_states</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="c1"># Combine the following pattern</span>
<span class="c1">#</span>
<span class="c1"># SiLU(FC(x)) + Gate(x)</span>
<span class="c1">#</span>
<span class="c1"># into:</span>
<span class="c1">#</span>
<span class="c1"># SwiGLU(FusedFC(x))</span>
<span class="n">p_dtype</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">gemm_swiglu_plugin</span>
<span class="n">use_fp8</span> <span class="o">=</span> <span class="n">p_dtype</span> <span class="o">==</span> <span class="s1">&#39;fp8&#39;</span>
<span class="k">assert</span> <span class="n">use_fp8</span><span class="p">,</span> <span class="s2">&quot;gemm_swiglu_plugin only supports fp8 now&quot;</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_fc_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_h_to_4h&quot;</span><span class="p">)</span>
<span class="n">mlp_gate_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_gate&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">mlp_fc_lora_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">mlp_gate_lora_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;LoRA not yet implemented for gemm_swiglu_plugin&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">!=</span> <span class="s1">&#39;silu&#39;</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Activation </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="si">}</span><span class="s2"> not yet implemented for gemm_swiglu_plugin&quot;</span>
<span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">bias</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;bias not yet implemented for gemm_swiglu_plugin fp8&quot;</span><span class="p">)</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span><span class="p">,</span>
<span class="n">FP8Linear</span><span class="p">),</span> <span class="s2">&quot;fp8 gemm_swiglu only supports fp8 weights&quot;</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proj</span><span class="p">,</span>
<span class="n">FP8RowLinear</span><span class="p">),</span> <span class="s2">&quot;fp8 gemm_swiglu only supports fp8 weights&quot;</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">shape</span> <span class="o">==</span> <span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">ffn_hidden_size</span> <span class="o">*</span> <span class="mi">2</span> <span class="o">//</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tp_size</span><span class="p">),</span> <span class="s2">&quot;fp8 gemm_swiglu only supports (k, n) weights&quot;</span>
<span class="n">scale_d0</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span><span class="o">.</span><span class="n">weights_scaling_factor</span><span class="o">.</span><span class="n">raw_value</span><span class="o">.</span><span class="n">item</span><span class="p">()</span> <span class="o">*</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span><span class="o">.</span><span class="n">activation_scaling_factor</span><span class="o">.</span><span class="n">raw_value</span><span class="o">.</span><span class="n">item</span><span class="p">())</span>
<span class="n">scale_d1</span> <span class="o">=</span> <span class="n">scale_d0</span>
<span class="n">scale_output</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">proj</span><span class="o">.</span><span class="n">activation_scaling_factor</span><span class="o">.</span><span class="n">raw_value</span><span class="o">.</span><span class="n">item</span><span class="p">(</span>
<span class="p">)</span>
<span class="n">activation_scaling_factor</span> <span class="o">=</span> <span class="n">cast</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span><span class="o">.</span><span class="n">activation_scaling_factor</span><span class="o">.</span><span class="n">value</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<span class="k">if</span> <span class="n">hidden_states</span><span class="o">.</span><span class="n">dtype</span> <span class="o">!=</span> <span class="n">trt</span><span class="o">.</span><span class="n">fp8</span><span class="p">:</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">quantize</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">activation_scaling_factor</span><span class="p">,</span>
<span class="s1">&#39;fp8&#39;</span><span class="p">)</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">gemm_swiglu</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">value</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">scale_d0</span><span class="p">,</span> <span class="n">scale_d1</span><span class="p">,</span> <span class="n">scale_output</span><span class="p">)</span>
<span class="k">return</span> <span class="n">inter</span></div>
<div class="viewcode-block" id="FusedGatedMLP.fc_gate">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.FusedGatedMLP.fc_gate">[docs]</a>
<span class="k">def</span> <span class="nf">fc_gate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hidden_states</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="c1"># Combine the following pattern</span>
<span class="c1">#</span>
<span class="c1"># SiLU(FC(x)) + Gate(x)</span>
<span class="c1">#</span>
<span class="c1"># into:</span>
<span class="c1">#</span>
<span class="c1"># SwiGLU(FusedFC(x))</span>
<span class="c1">#</span>
<span class="c1"># Upside is we don&#39;t need to modify 4 different weight loading paths just to concat weights</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fused_fc</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">lora_result</span> <span class="o">=</span> <span class="n">fc_gate_lora</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">lora</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="p">)</span>
<span class="k">if</span> <span class="n">lora_result</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">inter</span> <span class="o">+</span> <span class="n">lora_result</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">==</span> <span class="s1">&#39;silu&#39;</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="s1">&#39;swiglu&#39;</span><span class="p">](</span><span class="n">inter</span><span class="p">)</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span> <span class="o">==</span> <span class="s1">&#39;gelu&#39;</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="n">ACT2FN</span><span class="p">[</span><span class="s1">&#39;geglu&#39;</span><span class="p">](</span><span class="n">inter</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Activation </span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">hidden_act</span><span class="si">}</span><span class="s2"> not yet implemented for FusedGatedMLP&quot;</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">inter</span></div>
<div class="viewcode-block" id="FusedGatedMLP.forward">
<a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.mlp.FusedGatedMLP.forward">[docs]</a>
<span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">hidden_states</span><span class="p">,</span>
<span class="n">lora_layer_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">reduce_fusion_params</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">AllReduceFusionParams</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">default_net</span><span class="p">()</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">gemm_swiglu_plugin</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc_gate_plugin</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc_gate</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">,</span> <span class="n">lora_layer_params</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">inter</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">inner_layernorm</span><span class="p">(</span><span class="n">inter</span><span class="p">)</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">lora_layer_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">mlp_proj_lora_params</span> <span class="o">=</span> <span class="n">lora_layer_params</span><span class="o">.</span><span class="n">get_runtime_params</span><span class="p">(</span>
<span class="mi">0</span><span class="p">,</span> <span class="s2">&quot;mlp_4h_to_h&quot;</span><span class="p">)</span>
<span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">proj</span><span class="p">(</span><span class="n">inter</span><span class="p">,</span>
<span class="n">lora_runtime_params</span><span class="o">=</span><span class="n">mlp_proj_lora_params</span><span class="p">,</span>
<span class="n">reduce_fusion_params</span><span class="o">=</span><span class="n">reduce_fusion_params</span><span class="p">)</span>
<span class="k">return</span> <span class="n">output</span></div>
</div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<jinja2.runtime.BlockReference object at 0x7fea0f936050>
<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>
Reference in New Issue View Git Blame Copy Permalink