diff --git a/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip b/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip
index 4b8034f4f..764090ea1 100644
Binary files a/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip and b/_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip differ
diff --git a/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip b/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip
index c6f01fc7d..3bac2ff8d 100644
Binary files a/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip and b/_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip differ
diff --git a/_images/sphx_glr_01-vector-add_001.png b/_images/sphx_glr_01-vector-add_001.png
index b725ba7aa..fb68362b7 100644
Binary files a/_images/sphx_glr_01-vector-add_001.png and b/_images/sphx_glr_01-vector-add_001.png differ
diff --git a/_images/sphx_glr_01-vector-add_thumb.png b/_images/sphx_glr_01-vector-add_thumb.png
index 202cabb80..b1392aa75 100644
Binary files a/_images/sphx_glr_01-vector-add_thumb.png and b/_images/sphx_glr_01-vector-add_thumb.png differ
diff --git a/_images/sphx_glr_02-fused-softmax_001.png b/_images/sphx_glr_02-fused-softmax_001.png
index d4c22aa46..41b367e84 100644
Binary files a/_images/sphx_glr_02-fused-softmax_001.png and b/_images/sphx_glr_02-fused-softmax_001.png differ
diff --git a/_images/sphx_glr_02-fused-softmax_thumb.png b/_images/sphx_glr_02-fused-softmax_thumb.png
index 1e6f27674..a345d3ab4 100644
Binary files a/_images/sphx_glr_02-fused-softmax_thumb.png and b/_images/sphx_glr_02-fused-softmax_thumb.png differ
diff --git a/_sources/getting-started/installation.rst.txt b/_sources/getting-started/installation.rst.txt
index 07c50ca06..b4e3fd262 100644
--- a/_sources/getting-started/installation.rst.txt
+++ b/_sources/getting-started/installation.rst.txt
@@ -2,17 +2,6 @@
 Installation
 ==============
 
---------------
-With Pip
---------------
-
-Triton can be installed directly from pip with the following command
-
-.. code-block:: python
-
-   pip install triton
-
-
 --------------
 From Source
 --------------
diff --git a/_sources/getting-started/tutorials/01-vector-add.rst.txt b/_sources/getting-started/tutorials/01-vector-add.rst.txt
index d5b5fd105..0fce2f538 100644
--- a/_sources/getting-started/tutorials/01-vector-add.rst.txt
+++ b/_sources/getting-started/tutorials/01-vector-add.rst.txt
@@ -268,7 +268,7 @@ We can now run the decorated function above. Pass `show_plots=True` to see the p
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  5.768 seconds)
+   **Total running time of the script:** ( 0 minutes  5.901 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:
diff --git a/_sources/getting-started/tutorials/02-fused-softmax.rst.txt b/_sources/getting-started/tutorials/02-fused-softmax.rst.txt
index ba7ff4e9e..88ddb1893 100644
--- a/_sources/getting-started/tutorials/02-fused-softmax.rst.txt
+++ b/_sources/getting-started/tutorials/02-fused-softmax.rst.txt
@@ -305,7 +305,7 @@ In the above plot, we can see that:
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** ( 0 minutes  21.653 seconds)
+   **Total running time of the script:** ( 0 minutes  21.805 seconds)
 
 
 .. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:
diff --git a/_sources/getting-started/tutorials/sg_execution_times.rst.txt b/_sources/getting-started/tutorials/sg_execution_times.rst.txt
index 7e482e257..5ac8db2ed 100644
--- a/_sources/getting-started/tutorials/sg_execution_times.rst.txt
+++ b/_sources/getting-started/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
 
 Computation times
 =================
-**00:27.420** total execution time for **getting-started_tutorials** files:
+**00:27.706** total execution time for **getting-started_tutorials** files:
 
 +-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 00:21.653 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 00:21.805 | 0.0 MB |
 +-----------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)       | 00:05.768 | 0.0 MB |
+| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``)       | 00:05.901 | 0.0 MB |
 +-----------------------------------------------------------------------------------------+-----------+--------+
diff --git a/getting-started/installation.html b/getting-started/installation.html
index 62d8475f7..ab22307fb 100644
--- a/getting-started/installation.html
+++ b/getting-started/installation.html
@@ -92,7 +92,6 @@
               <p class="caption"><span class="caption-text">Getting Started</span></p>
 <ul class="current">
 <li class="toctree-l1 current"><a class="current reference internal" href="#">Installation</a><ul>
-<li class="toctree-l2"><a class="reference internal" href="#with-pip">With Pip</a></li>
 <li class="toctree-l2"><a class="reference internal" href="#from-source">From Source</a><ul>
 <li class="toctree-l3"><a class="reference internal" href="#python-package">Python Package</a></li>
 <li class="toctree-l3"><a class="reference internal" href="#c-package">C++ Package</a></li>
@@ -170,13 +169,6 @@
             
   <div class="section" id="installation">
 <h1>Installation<a class="headerlink" href="#installation" title="Permalink to this headline">¶</a></h1>
-<div class="section" id="with-pip">
-<h2>With Pip<a class="headerlink" href="#with-pip" title="Permalink to this headline">¶</a></h2>
-<p>Triton can be installed directly from pip with the following command</p>
-<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">pip</span> <span class="n">install</span> <span class="n">triton</span>
-</pre></div>
-</div>
-</div>
 <div class="section" id="from-source">
 <h2>From Source<a class="headerlink" href="#from-source" title="Permalink to this headline">¶</a></h2>
 <div class="section" id="python-package">
diff --git a/getting-started/tutorials/01-vector-add.html b/getting-started/tutorials/01-vector-add.html
index 76283b13e..974dc871e 100644
--- a/getting-started/tutorials/01-vector-add.html
+++ b/getting-started/tutorials/01-vector-add.html
@@ -355,7 +355,7 @@ for different problem sizes.</p>
 </pre></div>
 </div>
 <img alt="vector-add-performance" class="sphx-glr-single-img" src="../../_images/sphx_glr_01-vector-add_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  5.768 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  5.901 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-01-vector-add-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/62d97d49a32414049819dd8bb8378080/01-vector-add.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">01-vector-add.py</span></code></a></p>
diff --git a/getting-started/tutorials/02-fused-softmax.html b/getting-started/tutorials/02-fused-softmax.html
index f9d5ee701..4e65bd1d4 100644
--- a/getting-started/tutorials/02-fused-softmax.html
+++ b/getting-started/tutorials/02-fused-softmax.html
@@ -386,7 +386,7 @@ This means that – when temporary data is too large to fit entirely in the GPU
 Note that our Triton kernel is not only faster than PyTorch’s CUDA kernel, it is also <strong>easier to read, understand and maintain</strong>.</p></li>
 </ul>
 </div></blockquote>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  21.653 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  21.805 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-02-fused-softmax-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../../_downloads/d91442ac2982c4e0cc3ab0f43534afbc/02-fused-softmax.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">02-fused-softmax.py</span></code></a></p>
diff --git a/getting-started/tutorials/sg_execution_times.html b/getting-started/tutorials/sg_execution_times.html
index 9ba276666..65d8511b8 100644
--- a/getting-started/tutorials/sg_execution_times.html
+++ b/getting-started/tutorials/sg_execution_times.html
@@ -160,7 +160,7 @@
             
   <div class="section" id="computation-times">
 <span id="sphx-glr-getting-started-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:27.420</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
+<p><strong>00:27.706</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
 <table class="docutils align-default">
 <colgroup>
 <col style="width: 82%" />
@@ -169,11 +169,11 @@
 </colgroup>
 <tbody>
 <tr class="row-odd"><td><p><a class="reference internal" href="02-fused-softmax.html#sphx-glr-getting-started-tutorials-02-fused-softmax-py"><span class="std std-ref">Fused Softmax</span></a> (<code class="docutils literal notranslate"><span class="pre">02-fused-softmax.py</span></code>)</p></td>
-<td><p>00:21.653</p></td>
+<td><p>00:21.805</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="01-vector-add.html#sphx-glr-getting-started-tutorials-01-vector-add-py"><span class="std std-ref">Vector Addition</span></a> (<code class="docutils literal notranslate"><span class="pre">01-vector-add.py</span></code>)</p></td>
-<td><p>00:05.768</p></td>
+<td><p>00:05.901</p></td>
 <td><p>0.0 MB</p></td>
 </tr>
 </tbody>
diff --git a/objects.inv b/objects.inv
index 2c44e87a0..27b7c41ce 100644
Binary files a/objects.inv and b/objects.inv differ
diff --git a/searchindex.js b/searchindex.js
index dbb4ef83d..56ec263db 100644
--- a/searchindex.js
+++ b/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["getting-started/installation","getting-started/tutorials/01-vector-add","getting-started/tutorials/02-fused-softmax","getting-started/tutorials/index","getting-started/tutorials/sg_execution_times","index"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":3,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":2,"sphinx.domains.rst":2,"sphinx.domains.std":1,sphinx:56},filenames:["getting-started/installation.rst","getting-started/tutorials/01-vector-add.rst","getting-started/tutorials/02-fused-softmax.rst","getting-started/tutorials/index.rst","getting-started/tutorials/sg_execution_times.rst","index.rst"],objects:{},objnames:{},objtypes:{},terms:{"1024":1,"10mn":2,"1823":2,"1984":1,"2019":1,"256":2,"2696":1,"2mn":2,"3076":1,"3713":1,"3mn":2,"4096":2,"420":4,"4940":1,"653":[2,4],"6682":1,"768":[1,4],"781":2,"7mn":2,"98432":1,"byte":2,"case":2,"class":[1,2],"float":[1,2],"function":[1,2],"import":[1,2],"int":[1,2],"return":[1,2],"true":[1,2],"void":[1,2],"while":0,For:1,The:[1,2],Used:[1,2],__expf:2,__global__:[1,2],_add:1,_softmax:2,_src:[1,2],about:[1,2],abov:[1,2],abs:1,access:1,achiev:1,add:[1,4],addit:[2,3,4],address:2,advantag:1,against:[1,2],aim:5,all:[2,3],allclos:2,alloc:1,allow:[1,2],almost:2,along:1,also:[0,1,2],amount:2,ani:2,api:[0,1],appli:[1,2],approxim:2,apt:0,arg:[1,2],argument:[1,2],around:2,arrai:1,assert:[1,2],assum:2,attribut:1,autograd:[1,2],automat:2,axi:[1,2],back:[1,2],backward:1,bandwidth:2,basic:[1,3],becaus:2,below:[1,3],bench:0,benchmark:0,benefit:2,best:1,between:1,binari:0,bit:2,block:[1,2],blockidx:1,bool:[1,2],bound:[1,2],build:0,built:1,cach:[1,2],callabl:1,can:[0,1,2],capabl:[2,5],cdiv:1,ceil:1,check:[1,2],chip:2,choic:5,chunk:1,citizen:1,click:[1,2],clone:0,cmake:0,code:[1,2,3],codegen:0,column:2,com:0,come:1,command:0,comment:1,compar:2,compil:[1,2,5],comput:5,concis:1,cond:1,condit:1,config:0,consid:2,consist:2,constraint:[1,2],context:1,contigu:1,contrari:1,control:1,coordin:1,copi:1,correct:1,correspond:[1,2],could:2,cours:1,creat:1,csv:1,ctx:[1,2],cuda:[1,2],custom:[0,1,2,5],data:[1,2],data_ptr:[1,2],dblock:1,declar:1,decor:1,def:[1,2],defin:[1,2],denom:2,denomin:2,dereferenc:1,detail:1,dev:0,devic:[1,2],dict:[1,2],differ:[1,2],dir:0,direct:0,directli:0,disk:1,divis:1,dllvm_config:0,dnn:5,do_bench:[1,2],doe:[1,2],done:0,download:[1,2,3],dram:2,driver:0,dtype:[1,2],each:[1,2],easi:1,easier:[1,2],education:2,element:[1,2],element_s:2,elementwis:2,empty_lik:[1,2],entir:2,environ:5,exampl:[1,2,3],execut:[1,4],exist:1,exp:2,expect:[1,2],exponenti:2,extens:1,f32_infin:2,far:2,fast:2,faster:2,few:1,file:[1,2,4],first:[1,5],fit:2,float32:[1,2],flow:1,follow:[0,2,5],forward:[1,2],found:0,from:[1,2],full:[1,2],fuse:[3,4],fusion:2,galleri:[1,2,3],gbp:[1,2],gener:[1,2,3],get:[0,1,2,4],get_program_id:[1,2],git:0,github:0,given:2,good:1,gpu:[2,5],greater:2,grid:[1,2],guard:2,guess:2,handl:2,hardwar:5,has:[1,2],have:2,helper:2,here:[0,1,2],highlight:1,how:[1,5],http:0,ident:2,imper:5,implement:[1,2],increas:1,index:2,indic:2,input:[1,2],instal:5,instanc:2,instead:[1,2],instruct:5,integr:0,interest:0,intermedi:0,intern:[0,2],ipynb:[1,2],irregular:2,its:2,jupyt:[1,2,3],just:[1,2],kei:[1,2],kernel:5,label:[1,2],lambda:[1,2],languag:[1,5],larg:2,larger:2,launch:[1,2],learn:[1,2,5],less:2,let:2,like:1,limit:2,line:[1,2],llvm:0,load:[1,2],logarithm:1,look:[2,5],macro:1,mai:[0,1],maintain:[1,2],make:[0,1,2],make_add_kernel:1,make_kernel:2,mani:1,manual_se:[1,2],mapl:1,matric:2,matrix:2,matter:1,max:[1,2],max_m:[1,2],maxim:5,maximum:1,mean:2,mechan:2,memori:[1,2],mention:2,method:1,min:2,min_m:[1,2],minut:[1,2],mkdir:0,model:1,modern:5,modifi:1,more:1,move:2,multipl:1,must:2,naiv:2,naive_softmax:2,name:[1,2],nativ:1,necessari:2,need:[1,2],nelement:2,next_power_of_2:2,none:2,normal:2,note:[0,1,2],notebook:[1,2,3],now:[1,2],num:2,number:[1,2],numer:2,object:1,obvious:2,offici:0,offset:1,onc:2,one:[2,3],onli:[1,2],oper:[1,2,3],ops:1,opt:[1,2],order:3,other:1,our:[1,2],out:[1,2],outperform:2,output:[1,2],overach:1,pad:2,paper:1,parallel:[1,5],paramet:1,parser:0,partial:2,pass:1,past:1,path:[0,1],per:2,perf_report:[1,2],perform:[1,2],pid:1,platform:5,plot:[0,1,2],plot_nam:[1,2],pointer:1,portabl:1,possibl:[1,2],power:2,practic:[1,2],pre:1,predic:2,predict:2,prefer:[1,2],pretti:1,previou:2,primit:1,print:[1,2],problem:1,process:1,processor:1,product:5,program:[1,2,5],properli:2,provid:[0,1,2,5],ptillet:0,ptr:1,pytest:0,python:[1,2,3],pytorch:[1,2],quit:2,rand:1,randn:2,rang:[1,2],raw:1,read:[2,3],recommend:3,reduct:2,refer:1,rel:1,represent:0,requir:2,result:[0,1,2],ret:2,retriev:1,round:2,row:2,run:[0,1,2,5],runtim:0,save:[1,2],save_path:1,script:[1,2],second:[1,2],see:[1,2],seem:1,sens:1,set:1,shape:[1,2],share:2,shortcut:1,should:1,show_plot:[1,2],shown:1,significantli:2,similar:[1,2],simpl:[1,2],simplest:3,singl:1,size:1,smaller:2,smallest:2,softmax:[3,4],sourc:[1,2,3],spec:2,speed:2,sphinx:[1,2,3],spmd:1,stabil:2,standard:1,start:3,started_tutori:4,staticmethod:[1,2],store:[1,2],stride:2,stride_xm:2,stride_ym:2,string:1,sudo:0,sum:[1,2],support:0,sure:[1,2],syntax:[1,2],take:[1,5],temporari:2,tensor:1,ternari:1,test:0,than:2,thei:1,them:1,theoret:2,thi:[0,1,2],thing:1,think:2,those:[0,1],though:2,three:1,through:3,throughput:5,tile:2,time:[1,2],tmp:0,too:2,total:[1,2,4],transfer:2,transform:1,triton:[0,1,2,3],tupl:1,tutori:[0,1,2,5],tutorials_jupyt:3,tutorials_python:3,twice:2,two:[1,2],type:1,understand:2,unit:0,usag:[0,2],use:[0,1,2],used:1,using:1,util:1,val_fals:1,val_tru:1,valid:1,valu:[1,2],valuabl:2,variou:3,vector:[2,3,4],veri:2,verifi:2,want:[0,1,2],wast:2,what:1,when:[1,2],where:2,whether:1,which:[1,2],whose:[1,2],wise:[1,2],without:1,won:2,word:1,work:2,would:2,write:[1,2,3,5],wrote:2,x_log:1,x_max:2,x_name:[1,2],x_val:[1,2],y_line:[1,2],y_name:[1,2],y_ref:2,y_tri:2,y_val:[1,2],ylabel:[1,2],you:[0,1,2,3],your:[0,5],zip:3},titles:["Installation","Vector Addition","Fused Softmax","Tutorials","Computation times","Welcome to Triton\u2019s documentation!"],titleterms:{With:0,addit:1,benchmark:[1,2],bind:[1,2],comput:[1,2,4],document:5,from:0,fuse:2,get:5,instal:0,kernel:[1,2],motiv:2,packag:0,pip:0,python:0,softmax:2,sourc:0,start:5,test:[1,2],time:4,torch:[1,2],triton:5,tutori:3,unit:[1,2],vector:1,welcom:5}})
\ No newline at end of file
+Search.setIndex({docnames:["getting-started/installation","getting-started/tutorials/01-vector-add","getting-started/tutorials/02-fused-softmax","getting-started/tutorials/index","getting-started/tutorials/sg_execution_times","index"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":3,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":2,"sphinx.domains.rst":2,"sphinx.domains.std":1,sphinx:56},filenames:["getting-started/installation.rst","getting-started/tutorials/01-vector-add.rst","getting-started/tutorials/02-fused-softmax.rst","getting-started/tutorials/index.rst","getting-started/tutorials/sg_execution_times.rst","index.rst"],objects:{},objnames:{},objtypes:{},terms:{"1024":1,"10mn":2,"1823":2,"1984":1,"2019":1,"256":2,"2696":1,"2mn":2,"3076":1,"3713":1,"3mn":2,"4096":2,"4940":1,"6682":1,"706":4,"781":2,"7mn":2,"805":[2,4],"901":[1,4],"98432":1,"byte":2,"case":2,"class":[1,2],"float":[1,2],"function":[1,2],"import":[1,2],"int":[1,2],"return":[1,2],"true":[1,2],"void":[1,2],"while":0,For:1,The:[1,2],Used:[1,2],__expf:2,__global__:[1,2],_add:1,_softmax:2,_src:[1,2],about:[1,2],abov:[1,2],abs:1,access:1,achiev:1,add:[1,4],addit:[2,3,4],address:2,advantag:1,against:[1,2],aim:5,all:[2,3],allclos:2,alloc:1,allow:[1,2],almost:2,along:1,also:[0,1,2],amount:2,ani:2,api:[0,1],appli:[1,2],approxim:2,apt:0,arg:[1,2],argument:[1,2],around:2,arrai:1,assert:[1,2],assum:2,attribut:1,autograd:[1,2],automat:2,axi:[1,2],back:[1,2],backward:1,bandwidth:2,basic:[1,3],becaus:2,below:[1,3],bench:0,benchmark:0,benefit:2,best:1,between:1,binari:0,bit:2,block:[1,2],blockidx:1,bool:[1,2],bound:[1,2],build:0,built:1,cach:[1,2],callabl:1,can:[0,1,2],capabl:[2,5],cdiv:1,ceil:1,check:[1,2],chip:2,choic:5,chunk:1,citizen:1,click:[1,2],clone:0,cmake:0,code:[1,2,3],codegen:0,column:2,com:0,come:1,command:0,comment:1,compar:2,compil:[1,2,5],comput:5,concis:1,cond:1,condit:1,config:0,consid:2,consist:2,constraint:[1,2],context:1,contigu:1,contrari:1,control:1,coordin:1,copi:1,correct:1,correspond:[1,2],could:2,cours:1,creat:1,csv:1,ctx:[1,2],cuda:[1,2],custom:[0,1,2,5],data:[1,2],data_ptr:[1,2],dblock:1,declar:1,decor:1,def:[1,2],defin:[1,2],denom:2,denomin:2,dereferenc:1,detail:1,dev:0,devic:[1,2],dict:[1,2],differ:[1,2],dir:0,direct:0,directli:0,disk:1,divis:1,dllvm_config:0,dnn:5,do_bench:[1,2],doe:[1,2],done:0,download:[1,2,3],dram:2,driver:0,dtype:[1,2],each:[1,2],easi:1,easier:[1,2],education:2,element:[1,2],element_s:2,elementwis:2,empty_lik:[1,2],entir:2,environ:5,exampl:[1,2,3],execut:[1,4],exist:1,exp:2,expect:[1,2],exponenti:2,extens:1,f32_infin:2,far:2,fast:2,faster:2,few:1,file:[1,2,4],first:[1,5],fit:2,float32:[1,2],flow:1,follow:[0,2,5],forward:[1,2],found:0,from:[1,2],full:[1,2],fuse:[3,4],fusion:2,galleri:[1,2,3],gbp:[1,2],gener:[1,2,3],get:[0,1,2,4],get_program_id:[1,2],git:0,github:0,given:2,good:1,gpu:[2,5],greater:2,grid:[1,2],guard:2,guess:2,handl:2,hardwar:5,has:[1,2],have:2,helper:2,here:[0,1,2],highlight:1,how:[1,5],http:0,ident:2,imper:5,implement:[1,2],increas:1,index:2,indic:2,input:[1,2],instal:5,instanc:2,instead:[1,2],instruct:5,integr:0,interest:0,intermedi:0,intern:[0,2],ipynb:[1,2],irregular:2,its:2,jupyt:[1,2,3],just:[1,2],kei:[1,2],kernel:5,label:[1,2],lambda:[1,2],languag:[1,5],larg:2,larger:2,launch:[1,2],learn:[1,2,5],less:2,let:2,like:1,limit:2,line:[1,2],llvm:0,load:[1,2],logarithm:1,look:[2,5],macro:1,mai:[0,1],maintain:[1,2],make:[0,1,2],make_add_kernel:1,make_kernel:2,mani:1,manual_se:[1,2],mapl:1,matric:2,matrix:2,matter:1,max:[1,2],max_m:[1,2],maxim:5,maximum:1,mean:2,mechan:2,memori:[1,2],mention:2,method:1,min:2,min_m:[1,2],minut:[1,2],mkdir:0,model:1,modern:5,modifi:1,more:1,move:2,multipl:1,must:2,naiv:2,naive_softmax:2,name:[1,2],nativ:1,necessari:2,need:[1,2],nelement:2,next_power_of_2:2,none:2,normal:2,note:[0,1,2],notebook:[1,2,3],now:[1,2],num:2,number:[1,2],numer:2,object:1,obvious:2,offici:0,offset:1,onc:2,one:[2,3],onli:[1,2],oper:[1,2,3],ops:1,opt:[1,2],order:3,other:1,our:[1,2],out:[1,2],outperform:2,output:[1,2],overach:1,pad:2,paper:1,parallel:[1,5],paramet:1,parser:0,partial:2,pass:1,past:1,path:[0,1],per:2,perf_report:[1,2],perform:[1,2],pid:1,pip:0,platform:5,plot:[0,1,2],plot_nam:[1,2],pointer:1,portabl:1,possibl:[1,2],power:2,practic:[1,2],pre:1,predic:2,predict:2,prefer:[1,2],pretti:1,previou:2,primit:1,print:[1,2],problem:1,process:1,processor:1,product:5,program:[1,2,5],properli:2,provid:[0,1,2,5],ptillet:0,ptr:1,pytest:0,python:[1,2,3],pytorch:[1,2],quit:2,rand:1,randn:2,rang:[1,2],raw:1,read:[2,3],recommend:3,reduct:2,refer:1,rel:1,represent:0,requir:2,result:[0,1,2],ret:2,retriev:1,round:2,row:2,run:[0,1,2,5],runtim:0,save:[1,2],save_path:1,script:[1,2],second:[1,2],see:[1,2],seem:1,sens:1,set:1,shape:[1,2],share:2,shortcut:1,should:1,show_plot:[1,2],shown:1,significantli:2,similar:[1,2],simpl:[1,2],simplest:3,singl:1,size:1,smaller:2,smallest:2,softmax:[3,4],sourc:[1,2,3],spec:2,speed:2,sphinx:[1,2,3],spmd:1,stabil:2,standard:1,start:3,started_tutori:4,staticmethod:[1,2],store:[1,2],stride:2,stride_xm:2,stride_ym:2,string:1,sudo:0,sum:[1,2],support:0,sure:[1,2],syntax:[1,2],take:[1,5],temporari:2,tensor:1,ternari:1,test:0,than:2,thei:1,them:1,theoret:2,thi:[0,1,2],thing:1,think:2,those:[0,1],though:2,three:1,through:3,throughput:5,tile:2,time:[1,2],tmp:0,too:2,total:[1,2,4],transfer:2,transform:1,triton:[0,1,2,3],tupl:1,tutori:[0,1,2,5],tutorials_jupyt:3,tutorials_python:3,twice:2,two:[1,2],type:1,understand:2,unit:0,usag:[0,2],use:[0,1,2],used:1,using:1,util:1,val_fals:1,val_tru:1,valid:1,valu:[1,2],valuabl:2,variou:3,vector:[2,3,4],veri:2,verifi:2,want:[0,1,2],wast:2,what:1,when:[1,2],where:2,whether:1,which:[1,2],whose:[1,2],wise:[1,2],without:1,won:2,word:1,work:2,would:2,write:[1,2,3,5],wrote:2,x_log:1,x_max:2,x_name:[1,2],x_val:[1,2],y_line:[1,2],y_name:[1,2],y_ref:2,y_tri:2,y_val:[1,2],ylabel:[1,2],you:[0,1,2,3],your:[0,5],zip:3},titles:["Installation","Vector Addition","Fused Softmax","Tutorials","Computation times","Welcome to Triton\u2019s documentation!"],titleterms:{addit:1,benchmark:[1,2],bind:[1,2],comput:[1,2,4],document:5,from:0,fuse:2,get:5,instal:0,kernel:[1,2],motiv:2,packag:0,python:0,softmax:2,sourc:0,start:5,test:[1,2],time:4,torch:[1,2],triton:5,tutori:3,unit:[1,2],vector:1,welcom:5}})
\ No newline at end of file