update gh-pages (#2271)

NVIDIA · Sep 30, 2024 · 61d2fc0 · 61d2fc0
1 parent f873055
commit 61d2fc0
Show file tree

Hide file tree

Showing 140 changed files with 13,347 additions and 6,384 deletions.
diff --git a/_cpp_gen/executor.html b/_cpp_gen/executor.html
diff --git a/_cpp_gen/runtime.html b/_cpp_gen/runtime.html
diff --git a/_downloads/408e9af6e2b04a79e78215bde246e8bc/model.py b/_downloads/408e9af6e2b04a79e78215bde246e8bc/model.py
diff --git a/_downloads/b6815cf245cc7dc7a26a6f727fdc2dc4/model.py b/_downloads/b6815cf245cc7dc7a26a6f727fdc2dc4/model.py
diff --git a/_modules/index.html b/_modules/index.html
@@ -79,6 +79,10 @@
 <li class="toctree-l1"><a class="reference internal" href="../_cpp_gen/executor.html">Executor</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../_cpp_gen/runtime.html">Runtime</a></li>
 </ul>
+<p class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="../commands/trtllm-build.html">trtllm-build</a></li>
+</ul>
 <p class="caption" role="heading"><span class="caption-text">Architecture</span></p>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="../architecture/overview.html">TensorRT-LLM Architecture</a></li>
@@ -151,6 +155,7 @@ <h1>All modules for which code is available</h1>
 <ul><li><a href="tensorrt_llm/bindings/executor.html">tensorrt_llm.bindings.executor</a></li>
 </ul><li><a href="tensorrt_llm/builder.html">tensorrt_llm.builder</a></li>
 <li><a href="tensorrt_llm/functional.html">tensorrt_llm.functional</a></li>
+<li><a href="tensorrt_llm/hlapi/build_cache.html">tensorrt_llm.hlapi.build_cache</a></li>
 <li><a href="tensorrt_llm/hlapi/llm.html">tensorrt_llm.hlapi.llm</a></li>
 <li><a href="tensorrt_llm/hlapi/utils.html">tensorrt_llm.hlapi.utils</a></li>
 <li><a href="tensorrt_llm/layers/activation.html">tensorrt_llm.layers.activation</a></li>
@@ -171,6 +176,7 @@ <h1>All modules for which code is available</h1>
 <li><a href="tensorrt_llm/models/cogvlm/model.html">tensorrt_llm.models.cogvlm.model</a></li>
 <li><a href="tensorrt_llm/models/dbrx/config.html">tensorrt_llm.models.dbrx.config</a></li>
 <li><a href="tensorrt_llm/models/dbrx/model.html">tensorrt_llm.models.dbrx.model</a></li>
+<li><a href="tensorrt_llm/models/deepseek_v1/model.html">tensorrt_llm.models.deepseek_v1.model</a></li>
 <li><a href="tensorrt_llm/models/dit/model.html">tensorrt_llm.models.dit.model</a></li>
 <li><a href="tensorrt_llm/models/enc_dec/model.html">tensorrt_llm.models.enc_dec.model</a></li>
 <li><a href="tensorrt_llm/models/falcon/config.html">tensorrt_llm.models.falcon.config</a></li>
@@ -213,7 +219,7 @@ <h1>All modules for which code is available</h1>
   <hr/>
 
   <div role="contentinfo">
-<jinja2.runtime.BlockReference object at 0x7f4251db89d0>
+<jinja2.runtime.BlockReference object at 0x7fb952c13e80>
 
 <div class="footer">
     <p>

diff --git a/_modules/tensorrt_llm/builder.html b/_modules/tensorrt_llm/builder.html
diff --git a/_modules/tensorrt_llm/functional.html b/_modules/tensorrt_llm/functional.html
diff --git a/_modules/tensorrt_llm/hlapi/build_cache.html b/_modules/tensorrt_llm/hlapi/build_cache.html
diff --git a/_modules/tensorrt_llm/hlapi/llm.html b/_modules/tensorrt_llm/hlapi/llm.html
diff --git a/_modules/tensorrt_llm/hlapi/utils.html b/_modules/tensorrt_llm/hlapi/utils.html
diff --git a/_modules/tensorrt_llm/layers/activation.html b/_modules/tensorrt_llm/layers/activation.html
@@ -79,6 +79,10 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/executor.html">Executor</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/runtime.html">Runtime</a></li>
 </ul>
+<p class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-build.html">trtllm-build</a></li>
+</ul>
 <p class="caption" role="heading"><span class="caption-text">Architecture</span></p>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="../../../architecture/overview.html">TensorRT-LLM Architecture</a></li>
@@ -185,7 +189,7 @@ <h1>Source code for tensorrt_llm.layers.activation</h1><div class="highlight"><p
   <hr/>
 
   <div role="contentinfo">
-<jinja2.runtime.BlockReference object at 0x7f4251cae3e0>
+<jinja2.runtime.BlockReference object at 0x7fb955a94c40>
 
 <div class="footer">
     <p>

diff --git a/_modules/tensorrt_llm/layers/attention.html b/_modules/tensorrt_llm/layers/attention.html
diff --git a/_modules/tensorrt_llm/layers/cast.html b/_modules/tensorrt_llm/layers/cast.html
@@ -79,6 +79,10 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/executor.html">Executor</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/runtime.html">Runtime</a></li>
 </ul>
+<p class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-build.html">trtllm-build</a></li>
+</ul>
 <p class="caption" role="heading"><span class="caption-text">Architecture</span></p>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="../../../architecture/overview.html">TensorRT-LLM Architecture</a></li>
@@ -192,7 +196,7 @@ <h1>Source code for tensorrt_llm.layers.cast</h1><div class="highlight"><pre>
   <hr/>
 
   <div role="contentinfo">
-<jinja2.runtime.BlockReference object at 0x7f4251bd7af0>
+<jinja2.runtime.BlockReference object at 0x7fb9557e2ec0>
 
 <div class="footer">
     <p>

diff --git a/_modules/tensorrt_llm/layers/conv.html b/_modules/tensorrt_llm/layers/conv.html
@@ -79,6 +79,10 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/executor.html">Executor</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/runtime.html">Runtime</a></li>
 </ul>
+<p class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-build.html">trtllm-build</a></li>
+</ul>
 <p class="caption" role="heading"><span class="caption-text">Architecture</span></p>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="../../../architecture/overview.html">TensorRT-LLM Architecture</a></li>
@@ -389,7 +393,7 @@ <h1>Source code for tensorrt_llm.layers.conv</h1><div class="highlight"><pre>
   <hr/>
 
   <div role="contentinfo">
-<jinja2.runtime.BlockReference object at 0x7f4251bd60e0>
+<jinja2.runtime.BlockReference object at 0x7fb971d97ac0>
 
 <div class="footer">
     <p>

diff --git a/_modules/tensorrt_llm/layers/embedding.html b/_modules/tensorrt_llm/layers/embedding.html
@@ -79,6 +79,10 @@
 <li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/executor.html">Executor</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../_cpp_gen/runtime.html">Runtime</a></li>
 </ul>
+<p class="caption" role="heading"><span class="caption-text">Command-Line Reference</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="../../../commands/trtllm-build.html">trtllm-build</a></li>
+</ul>
 <p class="caption" role="heading"><span class="caption-text">Architecture</span></p>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="../../../architecture/overview.html">TensorRT-LLM Architecture</a></li>
@@ -250,15 +254,10 @@ <h1>Source code for tensorrt_llm.layers.embedding</h1><div class="highlight"><pr
 <div class="viewcode-block" id="Embedding.postprocess">
 <a class="viewcode-back" href="../../../python-api/tensorrt_llm.layers.html#tensorrt_llm.layers.embedding.Embedding.postprocess">[docs]</a>
     <span class="k">def</span> <span class="nf">postprocess</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tllm_key</span><span class="p">,</span> <span class="n">weights</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
-        <span class="n">config</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;config&quot;</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
         <span class="k">if</span> <span class="n">weights</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
             <span class="k">return</span> <span class="p">{}</span>
         <span class="n">weights</span> <span class="o">=</span> <span class="n">weights</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">str_dtype_to_torch</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dtype</span><span class="p">))</span>
-        <span class="k">if</span> <span class="n">config</span><span class="o">.</span><span class="n">share_embedding_table</span><span class="p">:</span>
-            <span class="k">return</span> <span class="p">{}</span>
-        <span class="k">else</span><span class="p">:</span>
-            <span class="n">weights</span> <span class="o">=</span> <span class="n">weights</span><span class="o">.</span><span class="n">clone</span><span class="p">()</span>
-            <span class="k">return</span> <span class="p">{</span><span class="n">tllm_key</span><span class="p">:</span> <span class="n">weights</span><span class="p">}</span></div>
+        <span class="k">return</span> <span class="p">{</span><span class="n">tllm_key</span><span class="p">:</span> <span class="n">weights</span><span class="p">}</span></div>
 </div>
 
 
@@ -348,7 +347,7 @@ <h1>Source code for tensorrt_llm.layers.embedding</h1><div class="highlight"><pr
   <hr/>
 
   <div role="contentinfo">
-<jinja2.runtime.BlockReference object at 0x7f4251bd61a0>
+<jinja2.runtime.BlockReference object at 0x7fb9705fe800>
 
 <div class="footer">
     <p>