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
42d0585493
TensorRT-LLMs/_modules/tensorrt_llm/models/recurrentgemma/model.html
nv-guomingz 42d0585493
doc:fix llm api reference blank issue. (#2669)
2025-01-08 14:45:46 +08:00

852 lines
107 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.models.recurrentgemma.model &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=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=9bcbadda"></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>
<li class="toctree-l1"><a class="reference internal" href="../../../../advanced/disaggregated-service.html">Disaggregated-Service (experimental)</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.models.recurrentgemma.model</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.models.recurrentgemma.model</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">collections</span> <span class="kn">import</span> <span class="n">OrderedDict</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">List</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">..._utils</span> <span class="kn">import</span> <span class="n">str_dtype_to_trt</span>
<span class="kn">from</span> <span class="nn">...functional</span> <span class="kn">import</span> <span class="p">(</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">arange</span><span class="p">,</span> <span class="n">concat</span><span class="p">,</span> <span class="n">expand</span><span class="p">,</span>
<span class="n">gather_last_token_logits</span><span class="p">,</span> <span class="n">shape</span><span class="p">,</span> <span class="n">tanh</span><span class="p">,</span> <span class="n">unsqueeze</span><span class="p">)</span>
<span class="kn">from</span> <span class="nn">...layers</span> <span class="kn">import</span> <span class="p">(</span><span class="n">Attention</span><span class="p">,</span> <span class="n">AttentionMaskType</span><span class="p">,</span> <span class="n">AttentionParams</span><span class="p">,</span>
<span class="n">ColumnLinear</span><span class="p">,</span> <span class="n">Embedding</span><span class="p">,</span> <span class="n">GatedMLP</span><span class="p">,</span> <span class="n">KeyValueCacheParams</span><span class="p">,</span>
<span class="n">PositionEmbeddingType</span><span class="p">,</span> <span class="n">Recurrent</span><span class="p">,</span> <span class="n">RmsNorm</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="p">,</span> <span class="n">ModuleList</span>
<span class="kn">from</span> <span class="nn">...plugin</span> <span class="kn">import</span> <span class="n">current_all_reduce_helper</span>
<span class="kn">from</span> <span class="nn">..generation_mixin</span> <span class="kn">import</span> <span class="n">GenerationMixin</span>
<span class="kn">from</span> <span class="nn">..modeling_utils</span> <span class="kn">import</span> <span class="p">(</span><span class="n">PretrainedConfig</span><span class="p">,</span> <span class="n">PretrainedModel</span><span class="p">,</span>
<span class="n">get_kv_cache_type_from_legacy</span><span class="p">)</span>
<span class="k">class</span> <span class="nc">ResidualLayer</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">config</span><span class="p">:</span> <span class="n">PretrainedConfig</span><span class="p">,</span> <span class="n">layer_idx</span><span class="p">:</span> <span class="nb">int</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">layer_type_len</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">layer_types</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">temporal_block_type</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">layer_types</span><span class="p">[</span><span class="n">layer_idx</span> <span class="o">%</span>
<span class="n">layer_type_len</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">input_layernorm</span> <span class="o">=</span> <span class="n">RmsNorm</span><span class="p">(</span><span class="n">normalized_shape</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">norm_epsilon</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">temporal_block_type</span> <span class="o">==</span> <span class="s1">&#39;recurrent&#39;</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">recurrent</span> <span class="o">=</span> <span class="n">Recurrent</span><span class="p">(</span><span class="n">width</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">lru_width</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">rnn_hidden_size</span><span class="p">,</span>
<span class="n">d_conv</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">conv_kernel</span><span class="p">,</span>
<span class="n">num_heads</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">num_attention_heads</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</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">config</span><span class="o">.</span><span class="n">mapping</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">config</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">)</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">temporal_block_type</span> <span class="o">==</span> <span class="s1">&#39;attention&#39;</span><span class="p">:</span>
<span class="n">layer_types</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">layer_types</span> <span class="o">*</span> <span class="p">(</span>
<span class="p">(</span><span class="n">layer_idx</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">//</span> <span class="n">layer_type_len</span><span class="p">)</span>
<span class="n">layer_types</span> <span class="o">=</span> <span class="n">layer_types</span> <span class="o">+</span> <span class="n">config</span><span class="o">.</span><span class="n">layer_types</span><span class="p">[</span><span class="mi">0</span><span class="p">:(</span>
<span class="p">(</span><span class="n">layer_idx</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> <span class="o">%</span> <span class="n">layer_type_len</span><span class="p">)]</span>
<span class="n">attention_layer_idx</span> <span class="o">=</span> <span class="n">layer_types</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="s1">&#39;attention&#39;</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span>
<span class="bp">self</span><span class="o">.</span><span class="n">attention</span> <span class="o">=</span> <span class="n">Attention</span><span class="p">(</span>
<span class="n">local_layer_idx</span><span class="o">=</span><span class="n">attention_layer_idx</span><span class="p">,</span>
<span class="n">hidden_size</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">num_attention_heads</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">num_attention_heads</span><span class="p">,</span>
<span class="n">num_kv_heads</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">num_key_value_heads</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">attention_mask_type</span><span class="o">=</span><span class="n">AttentionMaskType</span><span class="o">.</span><span class="n">causal</span><span class="p">,</span>
<span class="n">position_embedding_type</span><span class="o">=</span><span class="n">PositionEmbeddingType</span><span class="o">.</span><span class="n">rope_gpt_neox</span><span class="p">,</span>
<span class="n">rotary_embedding_percentage</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">rotary_pct</span><span class="p">,</span>
<span class="n">tp_group</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">mapping</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">config</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span><span class="p">,</span>
<span class="n">tp_rank</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">mapping</span><span class="o">.</span><span class="n">tp_rank</span><span class="p">,</span>
<span class="n">quant_mode</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">quant_mode</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">dense_bias</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">&#39;RecurrentGemma only support &quot;recurrent&quot; and &quot;attention&quot; blocks.&#39;</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">post_layernorm</span> <span class="o">=</span> <span class="n">RmsNorm</span><span class="p">(</span><span class="n">normalized_shape</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">norm_epsilon</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">mlp</span> <span class="o">=</span> <span class="n">GatedMLP</span><span class="p">(</span><span class="n">hidden_size</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">ffn_hidden_size</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">intermediate_size</span><span class="p">,</span>
<span class="n">hidden_act</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_act</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</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">config</span><span class="o">.</span><span class="n">mapping</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">config</span><span class="o">.</span><span class="n">mapping</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">config</span><span class="o">.</span><span class="n">quant_mode</span><span class="p">)</span>
<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">use_cache</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">attention_mask</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">kv_cache_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">attention_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">conv_state</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">lru_state</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">host_request_types</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">last_token_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">host_context_lengths</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">slot_mapping</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">conv_indices</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">residual</span> <span class="o">=</span> <span class="n">hidden_states</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">input_layernorm</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">temporal_block_type</span> <span class="o">==</span> <span class="s1">&#39;recurrent&#39;</span><span class="p">:</span>
<span class="n">temporal_output</span><span class="p">,</span> <span class="n">present_conv</span><span class="p">,</span> <span class="n">present_lru</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">recurrent</span><span class="p">(</span>
<span class="n">hidden_states</span><span class="p">,</span>
<span class="n">conv_state</span><span class="o">=</span><span class="n">conv_state</span><span class="p">,</span>
<span class="n">lru_state</span><span class="o">=</span><span class="n">lru_state</span><span class="p">,</span>
<span class="n">host_request_types</span><span class="o">=</span><span class="n">host_request_types</span><span class="p">,</span>
<span class="n">last_token_ids</span><span class="o">=</span><span class="n">last_token_ids</span><span class="p">,</span>
<span class="n">host_context_lengths</span><span class="o">=</span><span class="n">host_context_lengths</span><span class="p">,</span>
<span class="n">slot_mapping</span><span class="o">=</span><span class="n">slot_mapping</span><span class="p">,</span>
<span class="n">conv_indices</span><span class="o">=</span><span class="n">conv_indices</span><span class="p">,</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">present_conv</span><span class="p">,</span> <span class="n">present_lru</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">temporal_block_type</span> <span class="o">==</span> <span class="s1">&#39;attention&#39;</span><span class="p">:</span>
<span class="n">temporal_output</span><span class="p">,</span> <span class="n">present_kv</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">attention</span><span class="p">(</span>
<span class="n">hidden_states</span><span class="p">,</span>
<span class="n">attention_mask</span><span class="o">=</span><span class="n">attention_mask</span><span class="p">,</span>
<span class="n">use_cache</span><span class="o">=</span><span class="n">use_cache</span><span class="p">,</span>
<span class="n">kv_cache_params</span><span class="o">=</span><span class="n">kv_cache_params</span><span class="p">,</span>
<span class="n">attention_params</span><span class="o">=</span><span class="n">attention_params</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">present_kv</span> <span class="o">=</span> <span class="kc">None</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">residual</span> <span class="o">+</span> <span class="n">temporal_output</span>
<span class="n">residual</span> <span class="o">=</span> <span class="n">hidden_states</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">post_layernorm</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mlp</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">residual</span> <span class="o">+</span> <span class="n">hidden_states</span>
<span class="k">return</span> <span class="n">hidden_states</span><span class="p">,</span> <span class="n">present_kv</span><span class="p">,</span> <span class="n">present_conv</span><span class="p">,</span> <span class="n">present_lru</span>
<span class="k">class</span> <span class="nc">RecurrentGemmaModel</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">config</span><span class="p">:</span> <span class="n">PretrainedConfig</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</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">d_conv</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">conv_kernel</span>
<span class="bp">self</span><span class="o">.</span><span class="n">lru_width</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">rnn_hidden_size</span>
<span class="n">n_layer</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">num_hidden_layers</span>
<span class="bp">self</span><span class="o">.</span><span class="n">vocab_embedding</span> <span class="o">=</span> <span class="n">Embedding</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">,</span>
<span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">layers</span> <span class="o">=</span> <span class="n">ModuleList</span><span class="p">(</span>
<span class="p">[</span><span class="n">ResidualLayer</span><span class="p">(</span><span class="n">config</span><span class="p">,</span> <span class="n">layer_idx</span><span class="o">=</span><span class="n">i</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="n">n_layer</span><span class="p">)])</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ln_f</span> <span class="o">=</span> <span class="n">RmsNorm</span><span class="p">(</span><span class="n">normalized_shape</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">norm_epsilon</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">config</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<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">input_ids</span><span class="p">,</span>
<span class="n">use_cache</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">attention_mask</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">kv_cache_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">attention_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">conv_states</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">lru_states</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">host_request_types</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">last_token_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">host_context_lengths</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">slot_mapping</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">vocab_embedding</span><span class="p">(</span><span class="n">input_ids</span><span class="p">)</span>
<span class="c1"># Get conv state indices</span>
<span class="n">indices</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="ow">not</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">mamba_conv1d_plugin</span><span class="p">:</span>
<span class="n">batch_size</span> <span class="o">=</span> <span class="n">shape</span><span class="p">(</span><span class="n">input_ids</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
<span class="n">indices</span> <span class="o">=</span> <span class="n">expand</span><span class="p">(</span>
<span class="n">unsqueeze</span><span class="p">(</span><span class="n">arange</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_conv</span> <span class="o">-</span> <span class="mi">1</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s1">&#39;int32&#39;</span><span class="p">),</span> <span class="mi">0</span><span class="p">),</span>
<span class="n">concat</span><span class="p">([</span><span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_conv</span> <span class="o">-</span> <span class="mi">1</span><span class="p">]))</span>
<span class="n">offsets</span> <span class="o">=</span> <span class="n">expand</span><span class="p">(</span><span class="n">unsqueeze</span><span class="p">(</span><span class="n">last_token_ids</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span>
<span class="n">concat</span><span class="p">([</span><span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_conv</span> <span class="o">-</span> <span class="mi">1</span><span class="p">]))</span>
<span class="n">indices</span> <span class="o">=</span> <span class="n">unsqueeze</span><span class="p">(</span><span class="n">indices</span> <span class="o">+</span> <span class="n">offsets</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="n">indices</span> <span class="o">=</span> <span class="n">expand</span><span class="p">(</span>
<span class="n">indices</span><span class="p">,</span> <span class="n">concat</span><span class="p">([</span><span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">lru_width</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_conv</span> <span class="o">-</span> <span class="mi">1</span><span class="p">]))</span>
<span class="n">present_kvs</span><span class="p">,</span> <span class="n">present_convs</span><span class="p">,</span> <span class="n">present_lrus</span> <span class="o">=</span> <span class="p">[],</span> <span class="p">[],</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">layer</span><span class="p">,</span> <span class="n">past_kv</span><span class="p">,</span> <span class="n">past_conv</span><span class="p">,</span> <span class="n">past_lru</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">layers</span><span class="p">,</span> <span class="n">kv_cache_params</span><span class="o">.</span><span class="n">past_key_value</span><span class="p">,</span> <span class="n">conv_states</span><span class="p">,</span>
<span class="n">lru_states</span><span class="p">):</span>
<span class="n">hidden_states</span><span class="p">,</span> <span class="n">present_kv</span><span class="p">,</span> <span class="n">present_conv</span><span class="p">,</span> <span class="n">present_lru</span> <span class="o">=</span> <span class="n">layer</span><span class="p">(</span>
<span class="n">hidden_states</span><span class="p">,</span>
<span class="n">use_cache</span><span class="p">,</span>
<span class="n">attention_mask</span><span class="p">,</span>
<span class="n">kv_cache_params</span><span class="o">=</span><span class="n">KeyValueCacheParams</span><span class="p">(</span>
<span class="n">past_key_value</span><span class="o">=</span><span class="p">[</span><span class="n">past_kv</span><span class="p">],</span>
<span class="n">host_past_key_value_lengths</span><span class="o">=</span><span class="n">kv_cache_params</span><span class="o">.</span>
<span class="n">host_past_key_value_lengths</span><span class="p">,</span>
<span class="n">host_max_attention_window_sizes</span><span class="o">=</span><span class="n">kv_cache_params</span><span class="o">.</span>
<span class="n">host_max_attention_window_sizes</span><span class="p">,</span>
<span class="n">host_sink_token_length</span><span class="o">=</span><span class="n">kv_cache_params</span><span class="o">.</span>
<span class="n">host_sink_token_length</span><span class="p">,</span>
<span class="n">kv_cache_block_offsets</span><span class="o">=</span><span class="n">kv_cache_params</span><span class="o">.</span>
<span class="n">kv_cache_block_offsets</span><span class="p">,</span>
<span class="n">host_kv_cache_block_offsets</span><span class="o">=</span><span class="n">kv_cache_params</span><span class="o">.</span>
<span class="n">host_kv_cache_block_offsets</span><span class="p">,</span>
<span class="n">host_kv_cache_pool_pointers</span><span class="o">=</span><span class="n">kv_cache_params</span><span class="o">.</span>
<span class="n">host_kv_cache_pool_pointers</span><span class="p">,</span>
<span class="n">host_kv_cache_pool_mapping</span><span class="o">=</span><span class="n">kv_cache_params</span><span class="o">.</span>
<span class="n">host_kv_cache_pool_mapping</span><span class="p">,</span>
<span class="n">cache_indirection</span><span class="o">=</span><span class="n">kv_cache_params</span><span class="o">.</span><span class="n">cache_indirection</span><span class="p">),</span>
<span class="n">attention_params</span><span class="o">=</span><span class="n">attention_params</span><span class="p">,</span>
<span class="n">conv_state</span><span class="o">=</span><span class="n">past_conv</span><span class="p">,</span>
<span class="n">lru_state</span><span class="o">=</span><span class="n">past_lru</span><span class="p">,</span>
<span class="n">host_request_types</span><span class="o">=</span><span class="n">host_request_types</span><span class="p">,</span>
<span class="n">last_token_ids</span><span class="o">=</span><span class="n">last_token_ids</span><span class="p">,</span>
<span class="n">host_context_lengths</span><span class="o">=</span><span class="n">host_context_lengths</span><span class="p">,</span>
<span class="n">slot_mapping</span><span class="o">=</span><span class="n">slot_mapping</span><span class="p">,</span>
<span class="n">conv_indices</span><span class="o">=</span><span class="n">indices</span><span class="p">)</span>
<span class="n">present_kvs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">present_kv</span><span class="p">)</span>
<span class="n">present_convs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">present_conv</span><span class="p">)</span>
<span class="n">present_lrus</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">present_lru</span><span class="p">)</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">ln_f</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="k">return</span> <span class="n">hidden_states</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">present_kvs</span><span class="p">),</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">present_convs</span><span class="p">),</span> <span class="nb">tuple</span><span class="p">(</span>
<span class="n">present_lrus</span><span class="p">)</span>
<div class="viewcode-block" id="RecurrentGemmaForCausalLM">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.RecurrentGemmaForCausalLM">[docs]</a>
<span class="k">class</span> <span class="nc">RecurrentGemmaForCausalLM</span><span class="p">(</span><span class="n">PretrainedModel</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">config</span><span class="p">:</span> <span class="n">PretrainedConfig</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">config</span><span class="p">)</span>
<span class="n">dtype</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">dtype</span>
<span class="n">logits_dtype</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">logits_dtype</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dtype</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dtype</span> <span class="o">=</span> <span class="n">str_dtype_to_trt</span><span class="p">(</span><span class="n">dtype</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</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="p">)</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="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">layer_types</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span>
<span class="n">layer_types</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">layer_types</span>
<span class="n">layer_types</span> <span class="o">=</span> <span class="n">layer_types</span> <span class="o">*</span> <span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">num_hidden_layers</span> <span class="o">//</span>
<span class="nb">len</span><span class="p">(</span><span class="n">layer_types</span><span class="p">))</span>
<span class="n">layer_types</span> <span class="o">=</span> <span class="n">layer_types</span> <span class="o">+</span> <span class="n">layer_types</span><span class="p">[</span><span class="mi">0</span><span class="p">:(</span><span class="n">config</span><span class="o">.</span><span class="n">num_hidden_layers</span> <span class="o">%</span>
<span class="nb">len</span><span class="p">(</span><span class="n">layer_types</span><span class="p">))]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">layer_types</span> <span class="o">=</span> <span class="n">layer_types</span>
<span class="bp">self</span><span class="o">.</span><span class="n">config</span> <span class="o">=</span> <span class="n">config</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gather_context_logits</span> <span class="o">=</span> <span class="kc">False</span>
<span class="bp">self</span><span class="o">.</span><span class="n">logits_soft_cap</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">logits_soft_cap</span>
<span class="c1"># Create constant attention parameters to be reused by all layers.</span>
<span class="n">Attention</span><span class="o">.</span><span class="n">create_attention_const_params</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">config</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">position_embedding_type</span> <span class="o">=</span> <span class="n">config</span><span class="o">.</span><span class="n">position_embedding_type</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">logits_dtype</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_logits_dtype</span> <span class="o">=</span> <span class="n">str_dtype_to_trt</span><span class="p">(</span><span class="n">logits_dtype</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">logits_dtype</span><span class="p">,</span> <span class="n">trt</span><span class="o">.</span><span class="n">DataType</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_logits_dtype</span> <span class="o">=</span> <span class="n">logits_dtype</span>
<span class="bp">self</span><span class="o">.</span><span class="n">transformer</span> <span class="o">=</span> <span class="n">RecurrentGemmaModel</span><span class="p">(</span><span class="n">config</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">lm_head</span> <span class="o">=</span> <span class="n">ColumnLinear</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">,</span>
<span class="n">config</span><span class="o">.</span><span class="n">vocab_size</span><span class="p">,</span>
<span class="n">bias</span><span class="o">=</span><span class="kc">False</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">config</span><span class="o">.</span><span class="n">mapping</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">config</span><span class="o">.</span><span class="n">mapping</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">True</span><span class="p">)</span>
<div class="viewcode-block" id="RecurrentGemmaForCausalLM.forward">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.RecurrentGemmaForCausalLM.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">input_ids</span><span class="p">,</span>
<span class="n">position_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">use_cache</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">attention_mask</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">kv_cache_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">attention_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">conv_states</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">rnn_states</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">host_request_types</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">last_token_ids</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">last_token_ids_for_logits</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">host_context_lengths</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">slot_mapping</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="c1"># fill attention params.</span>
<span class="n">attention_params</span> <span class="o">=</span> <span class="n">Attention</span><span class="o">.</span><span class="n">fill_attention_params</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span> <span class="n">attention_params</span><span class="p">)</span>
<span class="n">hidden_states</span><span class="p">,</span> <span class="n">present_kvs</span><span class="p">,</span> <span class="n">present_convs</span><span class="p">,</span> <span class="n">present_rnns</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">transformer</span><span class="p">(</span>
<span class="n">input_ids</span><span class="p">,</span> <span class="n">use_cache</span><span class="p">,</span> <span class="n">attention_mask</span><span class="p">,</span> <span class="n">kv_cache_params</span><span class="p">,</span>
<span class="n">attention_params</span><span class="p">,</span> <span class="n">conv_states</span><span class="p">,</span> <span class="n">rnn_states</span><span class="p">,</span> <span class="n">host_request_types</span><span class="p">,</span>
<span class="n">last_token_ids</span><span class="p">,</span> <span class="n">host_context_lengths</span><span class="p">,</span> <span class="n">slot_mapping</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">gather_context_logits</span><span class="p">:</span>
<span class="n">hidden_states</span> <span class="o">=</span> <span class="n">gather_last_token_logits</span><span class="p">(</span>
<span class="n">hidden_states</span><span class="p">,</span> <span class="n">last_token_ids_for_logits</span><span class="p">,</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">remove_input_padding</span><span class="p">)</span>
<span class="n">lm_logits</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">lm_head</span><span class="p">(</span><span class="n">hidden_states</span><span class="p">)</span>
<span class="n">lm_logits</span> <span class="o">=</span> <span class="n">tanh</span><span class="p">(</span>
<span class="n">lm_logits</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">logits_soft_cap</span><span class="p">)</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">logits_soft_cap</span>
<span class="n">lm_logits</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="s1">&#39;logits&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_logits_dtype</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</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">paged_kv_cache</span><span class="p">:</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">present_kv</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">present_kvs</span><span class="p">):</span>
<span class="k">if</span> <span class="n">present_kv</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">present_kv</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="sa">f</span><span class="s1">&#39;present_key_value_</span><span class="si">{</span><span class="n">i</span><span class="si">}</span><span class="s1">&#39;</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="ow">not</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">paged_state</span><span class="p">:</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">present_conv</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">present_convs</span><span class="p">):</span>
<span class="k">if</span> <span class="n">present_conv</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">present_conv</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="sa">f</span><span class="s1">&#39;present_conv_state_</span><span class="si">{</span><span class="n">i</span><span class="si">}</span><span class="s1">&#39;</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">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">present_rnn</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">present_rnns</span><span class="p">):</span>
<span class="k">if</span> <span class="n">present_rnn</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">present_rnn</span><span class="o">.</span><span class="n">mark_output</span><span class="p">(</span><span class="sa">f</span><span class="s1">&#39;present_rnn_state_</span><span class="si">{</span><span class="n">i</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="n">str_dtype_to_trt</span><span class="p">(</span><span class="s1">&#39;float32&#39;</span><span class="p">))</span>
<span class="k">return</span> <span class="p">(</span><span class="n">lm_logits</span><span class="p">,</span> <span class="n">present_kvs</span><span class="p">,</span> <span class="n">present_convs</span><span class="p">,</span> <span class="n">present_rnns</span><span class="p">)</span></div>
<div class="viewcode-block" id="RecurrentGemmaForCausalLM.prepare_recurrent_inputs">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.RecurrentGemmaForCausalLM.prepare_recurrent_inputs">[docs]</a>
<span class="k">def</span> <span class="nf">prepare_recurrent_inputs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">max_batch_size</span><span class="p">,</span> <span class="n">num_profiles</span><span class="p">,</span> <span class="n">mapping</span><span class="p">):</span>
<span class="n">use_mamba_conv1d_plugin</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">(</span>
<span class="p">)</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">mamba_conv1d_plugin</span>
<span class="n">default_range</span> <span class="o">=</span> <span class="n">GenerationMixin</span><span class="o">.</span><span class="n">default_range</span>
<span class="n">batch_range</span> <span class="o">=</span> <span class="p">[</span><span class="n">default_range</span><span class="p">(</span><span class="n">max_batch_size</span><span class="p">)]</span> <span class="o">*</span> <span class="n">num_profiles</span>
<span class="n">conv_states</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">rnn_states</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">dim</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">rnn_hidden_size</span> <span class="o">//</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span>
<span class="k">if</span> <span class="n">use_mamba_conv1d_plugin</span><span class="p">:</span>
<span class="n">conv_state_dim_range</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">([</span>
<span class="p">(</span><span class="s1">&#39;batch_size&#39;</span><span class="p">,</span> <span class="n">batch_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;kernel_size&#39;</span><span class="p">,</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">conv_kernel</span> <span class="o">-</span> <span class="mi">1</span><span class="p">]</span> <span class="o">*</span> <span class="n">num_profiles</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;dim_size&#39;</span><span class="p">,</span> <span class="p">[</span><span class="n">dim</span><span class="p">]</span> <span class="o">*</span> <span class="n">num_profiles</span><span class="p">),</span>
<span class="p">])</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">conv_state_dim_range</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">([</span>
<span class="p">(</span><span class="s1">&#39;batch_size&#39;</span><span class="p">,</span> <span class="n">batch_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;dim_size&#39;</span><span class="p">,</span> <span class="p">[</span><span class="n">dim</span><span class="p">]</span> <span class="o">*</span> <span class="n">num_profiles</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;kernel_size&#39;</span><span class="p">,</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">conv_kernel</span> <span class="o">-</span> <span class="mi">1</span><span class="p">]</span> <span class="o">*</span> <span class="n">num_profiles</span><span class="p">),</span>
<span class="p">])</span>
<span class="n">rnn_state_dim_range</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">([</span>
<span class="p">(</span><span class="s1">&#39;batch_size&#39;</span><span class="p">,</span> <span class="n">batch_range</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;state_size&#39;</span><span class="p">,</span> <span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">*</span> <span class="n">num_profiles</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;dim_size&#39;</span><span class="p">,</span> <span class="p">[</span><span class="n">dim</span><span class="p">]</span> <span class="o">*</span> <span class="n">num_profiles</span><span class="p">),</span>
<span class="p">])</span>
<span class="n">one_dim_range</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">([</span>
<span class="p">(</span><span class="s1">&#39;buffer_count&#39;</span><span class="p">,</span> <span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">*</span> <span class="n">num_profiles</span><span class="p">),</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">config</span><span class="o">.</span><span class="n">num_hidden_layers</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_types</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">==</span> <span class="s1">&#39;recurrent&#39;</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">paged_state</span><span class="p">:</span>
<span class="n">conv_state</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="sa">f</span><span class="s1">&#39;conv_state_ptr_</span><span class="si">{</span><span class="n">i</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">str_dtype_to_trt</span><span class="p">(</span><span class="s1">&#39;int64&#39;</span><span class="p">),</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">one_dim_range</span><span class="p">)</span>
<span class="n">rnn_state</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="sa">f</span><span class="s1">&#39;rnn_state_ptr_</span><span class="si">{</span><span class="n">i</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">str_dtype_to_trt</span><span class="p">(</span><span class="s1">&#39;int64&#39;</span><span class="p">),</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">one_dim_range</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="n">use_mamba_conv1d_plugin</span><span class="p">:</span>
<span class="n">conv_state</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="sa">f</span><span class="s1">&#39;past_conv_state_</span><span class="si">{</span><span class="n">i</span><span class="si">}</span><span class="s1">&#39;</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">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">conv_kernel</span> <span class="o">-</span> <span class="mi">1</span><span class="p">,</span> <span class="n">dim</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">conv_state_dim_range</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">conv_state</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="sa">f</span><span class="s1">&#39;past_conv_state_</span><span class="si">{</span><span class="n">i</span><span class="si">}</span><span class="s1">&#39;</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">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="n">dim</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">conv_kernel</span> <span class="o">-</span> <span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">conv_state_dim_range</span><span class="p">)</span>
<span class="n">rnn_state</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="sa">f</span><span class="s1">&#39;past_rnn_state_</span><span class="si">{</span><span class="n">i</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">str_dtype_to_trt</span><span class="p">(</span><span class="s1">&#39;float32&#39;</span><span class="p">),</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">dim</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">rnn_state_dim_range</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">conv_state</span><span class="p">,</span> <span class="n">rnn_state</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span>
<span class="n">conv_states</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">conv_state</span><span class="p">)</span>
<span class="n">rnn_states</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">rnn_state</span><span class="p">)</span>
<span class="n">slot_mapping</span> <span class="o">=</span> <span class="kc">None</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">paged_state</span><span class="p">:</span>
<span class="n">slot_mapping</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;slot_mapping&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([(</span><span class="s1">&#39;batch_size&#39;</span><span class="p">,</span> <span class="n">batch_range</span><span class="p">)]),</span>
<span class="p">)</span>
<span class="n">return_dict</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;conv_states&#39;</span><span class="p">:</span> <span class="n">conv_states</span><span class="p">,</span>
<span class="s1">&#39;rnn_states&#39;</span><span class="p">:</span> <span class="n">rnn_states</span><span class="p">,</span>
<span class="s1">&#39;slot_mapping&#39;</span><span class="p">:</span> <span class="n">slot_mapping</span><span class="p">,</span>
<span class="p">}</span>
<span class="k">return</span> <span class="n">return_dict</span></div>
<div class="viewcode-block" id="RecurrentGemmaForCausalLM.prepare_inputs">
<a class="viewcode-back" href="../../../../python-api/tensorrt_llm.models.html#tensorrt_llm.models.RecurrentGemmaForCausalLM.prepare_inputs">[docs]</a>
<span class="k">def</span> <span class="nf">prepare_inputs</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">max_batch_size</span><span class="p">,</span>
<span class="n">max_input_len</span><span class="p">,</span>
<span class="n">max_seq_len</span><span class="p">,</span>
<span class="n">max_num_tokens</span><span class="p">,</span>
<span class="n">use_cache</span><span class="p">,</span>
<span class="n">max_beam_width</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">,</span>
<span class="n">opt_num_tokens</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">opt_batch_size</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span>
<span class="n">prompt_embedding_table_size</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span>
<span class="n">max_draft_len</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span>
<span class="n">gather_context_logits</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
<span class="n">gather_generation_logits</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
<span class="n">lora_target_modules</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">speculative_decoding_draft_tokens_external</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&#39;&#39;&#39;@brief: Prepare inputs Tensors for the model, the given sizes are used to determine the</span>
<span class="sd"> ranges of the dimensions of when using TRT dynamic shapes.</span>
<span class="sd"> @return: a list contains values which can be fed into the self.forward()</span>
<span class="sd"> &#39;&#39;&#39;</span>
<span class="k">assert</span> <span class="n">speculative_decoding_draft_tokens_external</span> <span class="o">==</span> <span class="kc">False</span><span class="p">,</span> \
<span class="s2">&quot;We don&#39;t support speculative decoding for the RecurrentGemma model.&quot;</span>
<span class="k">assert</span> <span class="n">max_beam_width</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">&quot;We don&#39;t support beam search for the RecurrentGemma model.&quot;</span>
<span class="n">remove_input_padding</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">remove_input_padding</span>
<span class="n">use_gpt_attention_plugin</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">(</span>
<span class="p">)</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">gpt_attention_plugin</span>
<span class="n">use_gemm_plugin</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_plugin</span>
<span class="n">paged_kv_cache</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">paged_kv_cache</span>
<span class="n">tokens_per_block</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">tokens_per_block</span>
<span class="n">multiple_profiles</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">multiple_profiles</span>
<span class="n">streamingllm</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">streamingllm</span>
<span class="n">use_mamba_conv1d_plugin</span> <span class="o">=</span> <span class="n">default_net</span><span class="p">(</span>
<span class="p">)</span><span class="o">.</span><span class="n">plugin_config</span><span class="o">.</span><span class="n">mamba_conv1d_plugin</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gather_context_logits</span> <span class="o">=</span> <span class="n">gather_context_logits</span>
<span class="n">mapping</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">mapping</span>
<span class="n">kv_cache_type</span> <span class="o">=</span> <span class="n">get_kv_cache_type_from_legacy</span><span class="p">(</span><span class="n">use_cache</span><span class="p">,</span> <span class="n">paged_kv_cache</span><span class="p">)</span>
<span class="c1"># basic inputs</span>
<span class="n">enable_ctx_gen_opt_profiles</span> <span class="o">=</span> <span class="n">GenerationMixin</span><span class="o">.</span><span class="n">has_ctx_gen_opt_profiles</span><span class="p">(</span>
<span class="n">use_gpt_attention_plugin</span><span class="o">=</span><span class="n">use_gpt_attention_plugin</span><span class="p">,</span>
<span class="n">use_gemm_plugin</span><span class="o">=</span><span class="n">use_gemm_plugin</span><span class="p">,</span>
<span class="n">remove_input_padding</span><span class="o">=</span><span class="n">remove_input_padding</span><span class="p">,</span>
<span class="n">kv_cache_type</span><span class="o">=</span><span class="n">kv_cache_type</span><span class="p">)</span>
<span class="n">num_profiles</span><span class="p">,</span> <span class="n">ranges</span> <span class="o">=</span> <span class="n">GenerationMixin</span><span class="o">.</span><span class="n">get_profiles_ranges</span><span class="p">(</span>
<span class="n">max_batch_size</span><span class="o">=</span><span class="n">max_batch_size</span><span class="p">,</span>
<span class="n">max_beam_width</span><span class="o">=</span><span class="n">max_beam_width</span><span class="p">,</span>
<span class="n">max_input_len</span><span class="o">=</span><span class="n">max_input_len</span><span class="p">,</span>
<span class="n">max_num_tokens</span><span class="o">=</span><span class="n">max_num_tokens</span><span class="p">,</span>
<span class="n">max_draft_len</span><span class="o">=</span><span class="n">max_draft_len</span><span class="p">,</span>
<span class="n">opt_batch_size</span><span class="o">=</span><span class="n">opt_batch_size</span><span class="p">,</span>
<span class="n">opt_num_tokens</span><span class="o">=</span><span class="n">opt_num_tokens</span><span class="p">,</span>
<span class="n">enable_ctx_gen_opt_profiles</span><span class="o">=</span><span class="n">enable_ctx_gen_opt_profiles</span><span class="p">,</span>
<span class="n">multiple_profiles</span><span class="o">=</span><span class="n">multiple_profiles</span><span class="p">,</span>
<span class="n">kv_cache_type</span><span class="o">=</span><span class="n">kv_cache_type</span><span class="p">)</span>
<span class="k">if</span> <span class="n">remove_input_padding</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">use_mamba_conv1d_plugin</span><span class="p">,</span> <span class="s2">&quot;mamba_conv1d_plugin is needed to support remove_input_padding&quot;</span>
<span class="n">input_ids</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;input_ids&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([</span>
<span class="p">(</span><span class="s1">&#39;num_tokens&#39;</span><span class="p">,</span> <span class="n">ranges</span><span class="p">[</span><span class="s1">&#39;num_tokens_range&#39;</span><span class="p">]),</span>
<span class="p">]))</span>
<span class="n">position_ids</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;position_ids&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([</span>
<span class="p">(</span><span class="s1">&#39;position_ids_num_tokens_range&#39;</span><span class="p">,</span>
<span class="n">ranges</span><span class="p">[</span><span class="s1">&#39;num_tokens_range&#39;</span><span class="p">]),</span>
<span class="p">]))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">input_ids</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;input_ids&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([</span>
<span class="p">(</span><span class="s1">&#39;batch_size_beam_width&#39;</span><span class="p">,</span>
<span class="n">ranges</span><span class="p">[</span><span class="s1">&#39;bb_range&#39;</span><span class="p">]),</span>
<span class="p">(</span><span class="s1">&#39;input_len&#39;</span><span class="p">,</span> <span class="n">ranges</span><span class="p">[</span><span class="s1">&#39;inlen_range&#39;</span><span class="p">]),</span>
<span class="p">]))</span>
<span class="n">position_ids</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;position_ids&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([</span>
<span class="p">(</span><span class="s1">&#39;batch_size_beam_width&#39;</span><span class="p">,</span>
<span class="n">ranges</span><span class="p">[</span><span class="s1">&#39;bb_range&#39;</span><span class="p">]),</span>
<span class="p">(</span><span class="s1">&#39;position_ids_inlen_range&#39;</span><span class="p">,</span>
<span class="n">ranges</span><span class="p">[</span><span class="s1">&#39;position_ids_inlen_range&#39;</span><span class="p">]),</span>
<span class="p">]))</span>
<span class="k">if</span> <span class="n">mapping</span><span class="o">.</span><span class="n">tp_size</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">current_all_reduce_helper</span><span class="p">()</span><span class="o">.</span><span class="n">set_workspace_tensor</span><span class="p">(</span>
<span class="n">mapping</span><span class="p">,</span> <span class="n">num_profiles</span><span class="p">)</span>
<span class="c1"># attention inputs</span>
<span class="n">attn_layer_idx</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">config</span><span class="o">.</span><span class="n">num_hidden_layers</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_types</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">==</span> <span class="s1">&#39;attention&#39;</span><span class="p">:</span>
<span class="n">attn_layer_idx</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">i</span><span class="p">)</span>
<span class="n">attention_inputs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">prepare_attention_inputs</span><span class="p">(</span>
<span class="n">max_batch_size</span><span class="o">=</span><span class="n">max_batch_size</span><span class="p">,</span>
<span class="n">max_beam_width</span><span class="o">=</span><span class="n">max_beam_width</span><span class="p">,</span>
<span class="n">max_input_len</span><span class="o">=</span><span class="n">max_input_len</span><span class="p">,</span>
<span class="n">max_seq_len</span><span class="o">=</span><span class="n">max_seq_len</span><span class="p">,</span>
<span class="n">num_kv_heads</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">num_key_value_heads</span><span class="p">,</span>
<span class="n">head_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">head_size</span><span class="p">,</span>
<span class="n">num_layers</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">num_hidden_layers</span><span class="p">,</span>
<span class="n">kv_dtype</span><span class="o">=</span><span class="n">str_dtype_to_trt</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">kv_dtype</span><span class="p">),</span>
<span class="n">num_profiles</span><span class="o">=</span><span class="n">num_profiles</span><span class="p">,</span>
<span class="n">enable_ctx_gen_opt_profiles</span><span class="o">=</span><span class="n">enable_ctx_gen_opt_profiles</span><span class="p">,</span>
<span class="n">remove_input_padding</span><span class="o">=</span><span class="n">remove_input_padding</span><span class="p">,</span>
<span class="n">use_gpt_attention_plugin</span><span class="o">=</span><span class="n">use_gpt_attention_plugin</span><span class="p">,</span>
<span class="n">kv_cache_type</span><span class="o">=</span><span class="n">kv_cache_type</span><span class="p">,</span>
<span class="n">tokens_per_block</span><span class="o">=</span><span class="n">tokens_per_block</span><span class="p">,</span>
<span class="n">mapping</span><span class="o">=</span><span class="n">mapping</span><span class="p">,</span>
<span class="n">streamingllm</span><span class="o">=</span><span class="n">streamingllm</span><span class="p">,</span>
<span class="n">attn_layer_idx</span><span class="o">=</span><span class="n">attn_layer_idx</span><span class="p">)</span>
<span class="c1"># recurrent inputs</span>
<span class="n">recurrent_inputs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">prepare_recurrent_inputs</span><span class="p">(</span>
<span class="n">max_batch_size</span><span class="o">=</span><span class="n">max_batch_size</span><span class="p">,</span>
<span class="n">num_profiles</span><span class="o">=</span><span class="n">num_profiles</span><span class="p">,</span>
<span class="n">mapping</span><span class="o">=</span><span class="n">mapping</span><span class="p">,</span>
<span class="p">)</span>
<span class="k">if</span> <span class="n">use_gpt_attention_plugin</span><span class="p">:</span>
<span class="n">host_request_types</span> <span class="o">=</span> <span class="n">attention_inputs</span><span class="p">[</span><span class="s1">&#39;host_request_types&#39;</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">host_request_types</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;host_request_types&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([(</span><span class="s1">&#39;batch_size_beam_width&#39;</span><span class="p">,</span>
<span class="n">ranges</span><span class="p">[</span><span class="s1">&#39;bb_range&#39;</span><span class="p">])]),</span>
<span class="p">)</span>
<span class="n">last_token_ids</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;last_token_ids&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([</span>
<span class="p">(</span><span class="s1">&#39;batch_size_last_token_ids&#39;</span><span class="p">,</span> <span class="n">ranges</span><span class="p">[</span><span class="s1">&#39;bbd_range&#39;</span><span class="p">]),</span>
<span class="p">]),</span>
<span class="p">)</span>
<span class="n">last_token_ids_for_logits</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">gather_context_logits</span><span class="p">:</span>
<span class="n">last_token_ids_for_logits</span> <span class="o">=</span> <span class="n">last_token_ids</span>
<span class="k">if</span> <span class="n">use_gpt_attention_plugin</span> <span class="ow">and</span> <span class="n">remove_input_padding</span><span class="p">:</span>
<span class="n">host_context_lengths</span> <span class="o">=</span> <span class="n">attention_inputs</span><span class="p">[</span><span class="s1">&#39;host_context_lengths&#39;</span><span class="p">]</span>
<span class="k">elif</span> <span class="n">remove_input_padding</span><span class="p">:</span>
<span class="n">host_context_lengths</span> <span class="o">=</span> <span class="n">Tensor</span><span class="p">(</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;host_context_lengths&#39;</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="n">trt</span><span class="o">.</span><span class="n">int32</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span>
<span class="n">dim_range</span><span class="o">=</span><span class="n">OrderedDict</span><span class="p">([(</span><span class="s1">&#39;batch_size_beam_width&#39;</span><span class="p">,</span>
<span class="n">ranges</span><span class="p">[</span><span class="s1">&#39;bb_range&#39;</span><span class="p">])]),</span>
<span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">host_context_lengths</span> <span class="o">=</span> <span class="kc">None</span>
<span class="n">return_dict</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;input_ids&#39;</span><span class="p">:</span>
<span class="n">input_ids</span><span class="p">,</span>
<span class="s1">&#39;position_ids&#39;</span><span class="p">:</span>
<span class="n">position_ids</span><span class="p">,</span>
<span class="s1">&#39;use_cache&#39;</span><span class="p">:</span>
<span class="kc">True</span><span class="p">,</span>
<span class="s1">&#39;attention_mask&#39;</span><span class="p">:</span>
<span class="n">attention_inputs</span><span class="p">[</span><span class="s1">&#39;attention_mask&#39;</span><span class="p">],</span>
<span class="s1">&#39;kv_cache_params&#39;</span><span class="p">:</span>
<span class="n">KeyValueCacheParams</span><span class="p">(</span>
<span class="n">past_key_value</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span><span class="s1">&#39;past_key_value&#39;</span><span class="p">],</span>
<span class="n">host_past_key_value_lengths</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span>
<span class="s1">&#39;host_past_key_value_lengths&#39;</span><span class="p">],</span>
<span class="n">host_max_attention_window_sizes</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span>
<span class="s1">&#39;host_max_attention_window_sizes&#39;</span><span class="p">],</span>
<span class="n">host_sink_token_length</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span>
<span class="s1">&#39;host_sink_token_length&#39;</span><span class="p">],</span>
<span class="n">kv_cache_block_offsets</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span>
<span class="s1">&#39;kv_cache_block_offsets&#39;</span><span class="p">],</span>
<span class="n">host_kv_cache_block_offsets</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span>
<span class="s1">&#39;host_kv_cache_block_offsets&#39;</span><span class="p">],</span>
<span class="n">host_kv_cache_pool_pointers</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span>
<span class="s1">&#39;host_kv_cache_pool_pointers&#39;</span><span class="p">],</span>
<span class="n">host_kv_cache_pool_mapping</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span>
<span class="s1">&#39;host_kv_cache_pool_mapping&#39;</span><span class="p">],</span>
<span class="n">cache_indirection</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span><span class="s1">&#39;cache_indirection&#39;</span><span class="p">],</span>
<span class="p">),</span>
<span class="s1">&#39;attention_params&#39;</span><span class="p">:</span>
<span class="n">AttentionParams</span><span class="p">(</span>
<span class="n">sequence_length</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span><span class="s1">&#39;sequence_length&#39;</span><span class="p">],</span>
<span class="n">context_lengths</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span><span class="s1">&#39;context_lengths&#39;</span><span class="p">],</span>
<span class="n">host_context_lengths</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span><span class="s1">&#39;host_context_lengths&#39;</span><span class="p">],</span>
<span class="n">max_context_length</span><span class="o">=</span><span class="n">max_input_len</span><span class="p">,</span>
<span class="n">host_request_types</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span><span class="s1">&#39;host_request_types&#39;</span><span class="p">],</span>
<span class="n">host_runtime_perf_knobs</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span>
<span class="s1">&#39;host_runtime_perf_knobs&#39;</span><span class="p">],</span>
<span class="n">host_context_progress</span><span class="o">=</span><span class="n">attention_inputs</span><span class="p">[</span><span class="s1">&#39;host_context_progress&#39;</span><span class="p">],</span>
<span class="p">),</span>
<span class="s1">&#39;conv_states&#39;</span><span class="p">:</span>
<span class="n">recurrent_inputs</span><span class="p">[</span><span class="s1">&#39;conv_states&#39;</span><span class="p">],</span>
<span class="s1">&#39;rnn_states&#39;</span><span class="p">:</span>
<span class="n">recurrent_inputs</span><span class="p">[</span><span class="s1">&#39;rnn_states&#39;</span><span class="p">],</span>
<span class="s1">&#39;host_request_types&#39;</span><span class="p">:</span>
<span class="n">host_request_types</span><span class="p">,</span>
<span class="s1">&#39;last_token_ids&#39;</span><span class="p">:</span>
<span class="n">last_token_ids</span><span class="p">,</span>
<span class="s1">&#39;last_token_ids_for_logits&#39;</span><span class="p">:</span>
<span class="n">last_token_ids_for_logits</span><span class="p">,</span>
<span class="s1">&#39;host_context_lengths&#39;</span><span class="p">:</span>
<span class="n">host_context_lengths</span><span class="p">,</span>
<span class="s1">&#39;slot_mapping&#39;</span><span class="p">:</span>
<span class="n">recurrent_inputs</span><span class="p">[</span><span class="s1">&#39;slot_mapping&#39;</span><span class="p">],</span>
<span class="p">}</span>
<span class="k">return</span> <span class="n">return_dict</span></div>
</div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<jinja2.runtime.BlockReference object at 0x7f1ac950ec60>
<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