update

assets/data/benchmarks/tp_scaling.html

@@ -0,0 +1,2 @@
+<div>                        <script type="text/javascript">window.PlotlyConfig = {MathJaxConfig: 'local'};</script>
+        <script charset="utf-8" src="https://cdn.plot.ly/plotly-2.32.0.min.js"></script>                <div id="1c31d751-4554-4c49-b217-074140865d95" class="plotly-graph-div" style="height:400px; width:1000px;"></div>            <script type="text/javascript">                                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById("1c31d751-4554-4c49-b217-074140865d95")) {                    Plotly.newPlot(                        "1c31d751-4554-4c49-b217-074140865d95",                        [{"marker":{"color":"#4ea5b7"},"name":"Tokens\u002fsec\u002fGPU","width":0.7,"x":["2","4","8","16","32"],"y":[13923.18,12420.76,10903.32,6245.6,2146.44],"type":"bar","xaxis":"x","yaxis":"y"},{"base":[12420.76],"marker":{"color":"#e889ab"},"name":"Performance Drop","showlegend":true,"width":0.0875,"x":["4"],"y":[1502.42],"type":"bar","xaxis":"x","yaxis":"y"},{"base":[10903.32],"marker":{"color":"#e889ab"},"showlegend":false,"width":0.0875,"x":["8"],"y":[1517.4400000000005],"type":"bar","xaxis":"x","yaxis":"y"},{"base":[6245.6],"marker":{"color":"#e889ab"},"showlegend":false,"width":0.0875,"x":["16"],"y":[4657.719999999999],"type":"bar","xaxis":"x","yaxis":"y"},{"base":[2146.44],"marker":{"color":"#e889ab"},"showlegend":false,"width":0.0875,"x":["32"],"y":[4099.16],"type":"bar","xaxis":"x","yaxis":"y"},{"marker":{"color":"#cec0fa"},"name":"Max Batch Size","text":["3","8","12","16","20"],"textposition":"inside","width":0.7,"x":["2","4","8","16","32"],"y":[3,8,12,16,20],"type":"bar","xaxis":"x2","yaxis":"y2"}],                        {"template":{"data":{"histogram2dcontour":[{"type":"histogram2dcontour","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"choropleth":[{"type":"choropleth","colorbar":{"outlinewidth":0,"ticks":""}}],"histogram2d":[{"type":"histogram2d","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"heatmap":[{"type":"heatmap","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"heatmapgl":[{"type":"heatmapgl","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"contourcarpet":[{"type":"contourcarpet","colorbar":{"outlinewidth":0,"ticks":""}}],"contour":[{"type":"contour","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"surface":[{"type":"surface","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"mesh3d":[{"type":"mesh3d","colorbar":{"outlinewidth":0,"ticks":""}}],"scatter":[{"fillpattern":{"fillmode":"overlay","size":10,"solidity":0.2},"type":"scatter"}],"parcoords":[{"type":"parcoords","line":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterpolargl":[{"type":"scatterpolargl","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"bar":[{"error_x":{"color":"#2a3f5f"},"error_y":{"color":"#2a3f5f"},"marker":{"line":{"color":"#E5ECF6","width":0.5},"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"bar"}],"scattergeo":[{"type":"scattergeo","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterpolar":[{"type":"scatterpolar","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"histogram":[{"marker":{"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"histogram"}],"scattergl":[{"type":"scattergl","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatter3d":[{"type":"scatter3d","line":{"colorbar":{"outlinewidth":0,"ticks":""}},"marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattermapbox":[{"type":"scattermapbox","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterternary":[{"type":"scatterternary","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattercarpet":[{"type":"scattercarpet","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"carpet":[{"aaxis":{"endlinecolor":"#2a3f5f","gridcolor":"white","linecolor":"white","minorgridcolor":"white","startlinecolor":"#2a3f5f"},"baxis":{"endlinecolor":"#2a3f5f","gridcolor":"white","linecolor":"white","minorgridcolor":"white","startlinecolor":"#2a3f5f"},"type":"carpet"}],"table":[{"cells":{"fill":{"color":"#EBF0F8"},"line":{"color":"white"}},"header":{"fill":{"color":"#C8D4E3"},"line":{"color":"white"}},"type":"table"}],"barpolar":[{"marker":{"line":{"color":"#E5ECF6","width":0.5},"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"barpolar"}],"pie":[{"automargin":true,"type":"pie"}]},"layout":{"autotypenumbers":"strict","colorway":["#636efa","#EF553B","#00cc96","#ab63fa","#FFA15A","#19d3f3","#FF6692","#B6E880","#FF97FF","#FECB52"],"font":{"color":"#2a3f5f"},"hovermode":"closest","hoverlabel":{"align":"left"},"paper_bgcolor":"white","plot_bgcolor":"#E5ECF6","polar":{"bgcolor":"#E5ECF6","angularaxis":{"gridcolor":"white","linecolor":"white","ticks":""},"radialaxis":{"gridcolor":"white","linecolor":"white","ticks":""}},"ternary":{"bgcolor":"#E5ECF6","aaxis":{"gridcolor":"white","linecolor":"white","ticks":""},"baxis":{"gridcolor":"white","linecolor":"white","ticks":""},"caxis":{"gridcolor":"white","linecolor":"white","ticks":""}},"coloraxis":{"colorbar":{"outlinewidth":0,"ticks":""}},"colorscale":{"sequential":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]],"sequentialminus":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]],"diverging":[[0,"#8e0152"],[0.1,"#c51b7d"],[0.2,"#de77ae"],[0.3,"#f1b6da"],[0.4,"#fde0ef"],[0.5,"#f7f7f7"],[0.6,"#e6f5d0"],[0.7,"#b8e186"],[0.8,"#7fbc41"],[0.9,"#4d9221"],[1,"#276419"]]},"xaxis":{"gridcolor":"white","linecolor":"white","ticks":"","title":{"standoff":15},"zerolinecolor":"white","automargin":true,"zerolinewidth":2},"yaxis":{"gridcolor":"white","linecolor":"white","ticks":"","title":{"standoff":15},"zerolinecolor":"white","automargin":true,"zerolinewidth":2},"scene":{"xaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2},"yaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2},"zaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2}},"shapedefaults":{"line":{"color":"#2a3f5f"}},"annotationdefaults":{"arrowcolor":"#2a3f5f","arrowhead":0,"arrowwidth":1},"geo":{"bgcolor":"white","landcolor":"#E5ECF6","subunitcolor":"white","showland":true,"showlakes":true,"lakecolor":"white"},"title":{"x":0.05},"mapbox":{"style":"light"}}},"xaxis":{"anchor":"y","domain":[0.0,0.45],"title":{"text":"Tensor Parallelism (TP)"},"showgrid":true,"gridcolor":"LightGray"},"yaxis":{"anchor":"x","domain":[0.0,1.0],"title":{"text":"Tokens\u002fsec\u002fGPU"},"showgrid":true,"gridcolor":"LightGray"},"xaxis2":{"anchor":"y2","domain":[0.55,1.0],"title":{"text":"Tensor Parallelism (TP)"},"showgrid":true,"gridcolor":"LightGray"},"yaxis2":{"anchor":"x2","domain":[0.0,1.0],"title":{"text":"Maximum Batch Size"},"showgrid":true,"gridcolor":"LightGray"},"annotations":[{"font":{"size":16},"showarrow":false,"text":"Throughput Scaling with TP (3B Model)","x":0.225,"xanchor":"center","xref":"paper","y":1.0,"yanchor":"bottom","yref":"paper"},{"font":{"size":16},"showarrow":false,"text":"Maximum Batch Size per TP Value","x":0.775,"xanchor":"center","xref":"paper","y":1.0,"yanchor":"bottom","yref":"paper"},{"font":{"color":"#e889ab"},"showarrow":false,"text":"-10.8%","x":1,"xanchor":"center","xref":"x","xshift":30,"y":13171.970000000001,"yanchor":"middle","yref":"y"},{"font":{"color":"#e889ab"},"showarrow":false,"text":"-12.2%","x":2,"xanchor":"center","xref":"x","xshift":30,"y":11662.04,"yanchor":"middle","yref":"y"},{"font":{"color":"#e889ab"},"showarrow":false,"text":"-42.7%","x":3,"xanchor":"center","xref":"x","xshift":30,"y":8574.46,"yanchor":"middle","yref":"y"},{"font":{"color":"#e889ab"},"showarrow":false,"text":"-65.6%","x":4,"xanchor":"center","xref":"x","xshift":30,"y":4196.02,"yanchor":"middle","yref":"y"}],"legend":{"x":0.55,"y":1.0},"width":1000,"height":400,"barmode":"stack"},                        {"responsive": true, "scrollZoom": false}                    )                };                            </script>        </div>

dist/assets/data/benchmarks/tp_scaling.html

@@ -0,0 +1,2 @@
+<div>                        <script type="text/javascript">window.PlotlyConfig = {MathJaxConfig: 'local'};</script>
+        <script charset="utf-8" src="https://cdn.plot.ly/plotly-2.32.0.min.js"></script>                <div id="1c31d751-4554-4c49-b217-074140865d95" class="plotly-graph-div" style="height:400px; width:1000px;"></div>            <script type="text/javascript">                                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById("1c31d751-4554-4c49-b217-074140865d95")) {                    Plotly.newPlot(                        "1c31d751-4554-4c49-b217-074140865d95",                        [{"marker":{"color":"#4ea5b7"},"name":"Tokens\u002fsec\u002fGPU","width":0.7,"x":["2","4","8","16","32"],"y":[13923.18,12420.76,10903.32,6245.6,2146.44],"type":"bar","xaxis":"x","yaxis":"y"},{"base":[12420.76],"marker":{"color":"#e889ab"},"name":"Performance Drop","showlegend":true,"width":0.0875,"x":["4"],"y":[1502.42],"type":"bar","xaxis":"x","yaxis":"y"},{"base":[10903.32],"marker":{"color":"#e889ab"},"showlegend":false,"width":0.0875,"x":["8"],"y":[1517.4400000000005],"type":"bar","xaxis":"x","yaxis":"y"},{"base":[6245.6],"marker":{"color":"#e889ab"},"showlegend":false,"width":0.0875,"x":["16"],"y":[4657.719999999999],"type":"bar","xaxis":"x","yaxis":"y"},{"base":[2146.44],"marker":{"color":"#e889ab"},"showlegend":false,"width":0.0875,"x":["32"],"y":[4099.16],"type":"bar","xaxis":"x","yaxis":"y"},{"marker":{"color":"#cec0fa"},"name":"Max Batch Size","text":["3","8","12","16","20"],"textposition":"inside","width":0.7,"x":["2","4","8","16","32"],"y":[3,8,12,16,20],"type":"bar","xaxis":"x2","yaxis":"y2"}],                        {"template":{"data":{"histogram2dcontour":[{"type":"histogram2dcontour","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"choropleth":[{"type":"choropleth","colorbar":{"outlinewidth":0,"ticks":""}}],"histogram2d":[{"type":"histogram2d","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"heatmap":[{"type":"heatmap","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"heatmapgl":[{"type":"heatmapgl","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"contourcarpet":[{"type":"contourcarpet","colorbar":{"outlinewidth":0,"ticks":""}}],"contour":[{"type":"contour","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"surface":[{"type":"surface","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"mesh3d":[{"type":"mesh3d","colorbar":{"outlinewidth":0,"ticks":""}}],"scatter":[{"fillpattern":{"fillmode":"overlay","size":10,"solidity":0.2},"type":"scatter"}],"parcoords":[{"type":"parcoords","line":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterpolargl":[{"type":"scatterpolargl","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"bar":[{"error_x":{"color":"#2a3f5f"},"error_y":{"color":"#2a3f5f"},"marker":{"line":{"color":"#E5ECF6","width":0.5},"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"bar"}],"scattergeo":[{"type":"scattergeo","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterpolar":[{"type":"scatterpolar","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"histogram":[{"marker":{"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"histogram"}],"scattergl":[{"type":"scattergl","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatter3d":[{"type":"scatter3d","line":{"colorbar":{"outlinewidth":0,"ticks":""}},"marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattermapbox":[{"type":"scattermapbox","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterternary":[{"type":"scatterternary","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattercarpet":[{"type":"scattercarpet","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"carpet":[{"aaxis":{"endlinecolor":"#2a3f5f","gridcolor":"white","linecolor":"white","minorgridcolor":"white","startlinecolor":"#2a3f5f"},"baxis":{"endlinecolor":"#2a3f5f","gridcolor":"white","linecolor":"white","minorgridcolor":"white","startlinecolor":"#2a3f5f"},"type":"carpet"}],"table":[{"cells":{"fill":{"color":"#EBF0F8"},"line":{"color":"white"}},"header":{"fill":{"color":"#C8D4E3"},"line":{"color":"white"}},"type":"table"}],"barpolar":[{"marker":{"line":{"color":"#E5ECF6","width":0.5},"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"barpolar"}],"pie":[{"automargin":true,"type":"pie"}]},"layout":{"autotypenumbers":"strict","colorway":["#636efa","#EF553B","#00cc96","#ab63fa","#FFA15A","#19d3f3","#FF6692","#B6E880","#FF97FF","#FECB52"],"font":{"color":"#2a3f5f"},"hovermode":"closest","hoverlabel":{"align":"left"},"paper_bgcolor":"white","plot_bgcolor":"#E5ECF6","polar":{"bgcolor":"#E5ECF6","angularaxis":{"gridcolor":"white","linecolor":"white","ticks":""},"radialaxis":{"gridcolor":"white","linecolor":"white","ticks":""}},"ternary":{"bgcolor":"#E5ECF6","aaxis":{"gridcolor":"white","linecolor":"white","ticks":""},"baxis":{"gridcolor":"white","linecolor":"white","ticks":""},"caxis":{"gridcolor":"white","linecolor":"white","ticks":""}},"coloraxis":{"colorbar":{"outlinewidth":0,"ticks":""}},"colorscale":{"sequential":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]],"sequentialminus":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]],"diverging":[[0,"#8e0152"],[0.1,"#c51b7d"],[0.2,"#de77ae"],[0.3,"#f1b6da"],[0.4,"#fde0ef"],[0.5,"#f7f7f7"],[0.6,"#e6f5d0"],[0.7,"#b8e186"],[0.8,"#7fbc41"],[0.9,"#4d9221"],[1,"#276419"]]},"xaxis":{"gridcolor":"white","linecolor":"white","ticks":"","title":{"standoff":15},"zerolinecolor":"white","automargin":true,"zerolinewidth":2},"yaxis":{"gridcolor":"white","linecolor":"white","ticks":"","title":{"standoff":15},"zerolinecolor":"white","automargin":true,"zerolinewidth":2},"scene":{"xaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2},"yaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2},"zaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2}},"shapedefaults":{"line":{"color":"#2a3f5f"}},"annotationdefaults":{"arrowcolor":"#2a3f5f","arrowhead":0,"arrowwidth":1},"geo":{"bgcolor":"white","landcolor":"#E5ECF6","subunitcolor":"white","showland":true,"showlakes":true,"lakecolor":"white"},"title":{"x":0.05},"mapbox":{"style":"light"}}},"xaxis":{"anchor":"y","domain":[0.0,0.45],"title":{"text":"Tensor Parallelism (TP)"},"showgrid":true,"gridcolor":"LightGray"},"yaxis":{"anchor":"x","domain":[0.0,1.0],"title":{"text":"Tokens\u002fsec\u002fGPU"},"showgrid":true,"gridcolor":"LightGray"},"xaxis2":{"anchor":"y2","domain":[0.55,1.0],"title":{"text":"Tensor Parallelism (TP)"},"showgrid":true,"gridcolor":"LightGray"},"yaxis2":{"anchor":"x2","domain":[0.0,1.0],"title":{"text":"Maximum Batch Size"},"showgrid":true,"gridcolor":"LightGray"},"annotations":[{"font":{"size":16},"showarrow":false,"text":"Throughput Scaling with TP (3B Model)","x":0.225,"xanchor":"center","xref":"paper","y":1.0,"yanchor":"bottom","yref":"paper"},{"font":{"size":16},"showarrow":false,"text":"Maximum Batch Size per TP Value","x":0.775,"xanchor":"center","xref":"paper","y":1.0,"yanchor":"bottom","yref":"paper"},{"font":{"color":"#e889ab"},"showarrow":false,"text":"-10.8%","x":1,"xanchor":"center","xref":"x","xshift":30,"y":13171.970000000001,"yanchor":"middle","yref":"y"},{"font":{"color":"#e889ab"},"showarrow":false,"text":"-12.2%","x":2,"xanchor":"center","xref":"x","xshift":30,"y":11662.04,"yanchor":"middle","yref":"y"},{"font":{"color":"#e889ab"},"showarrow":false,"text":"-42.7%","x":3,"xanchor":"center","xref":"x","xshift":30,"y":8574.46,"yanchor":"middle","yref":"y"},{"font":{"color":"#e889ab"},"showarrow":false,"text":"-65.6%","x":4,"xanchor":"center","xref":"x","xshift":30,"y":4196.02,"yanchor":"middle","yref":"y"}],"legend":{"x":0.55,"y":1.0},"width":1000,"height":400,"barmode":"stack"},                        {"responsive": true, "scrollZoom": false}                    )                };                            </script>        </div>

dist/index.html

@@ -849,7 +849,7 @@
 
         <p>In practice a small example of the operation looks like this:</p>
 
-        <p><img alt="image.png" src="/assets/images/tp_diagram.png" /></p>
+        <p><img class"l-body" alt="TP diagram" src="/assets/images/tp_diagram.svg" /></p>
 
         <p>Let’s see how we can parallelise this operation! In tensor parallelism, tensors will be split into N shards along a particular dimension and distributed across N GPUs. Matrices can be split either on the column part or row part leading to row and column parallelism. One thing we’ll see in the following is that choosing row or column sharding will require different communications primitives.</p>
 
@@ -911,7 +911,16 @@
 
         <p>Tensor parallelism does help reduce activation memory for the matrix multiplications since the intermediate activations are sharded across GPUs. However, we still need to gather the full activations for operations like LayerNorm, which means we're not getting the full memory benefits we could. Additionally, it introduces significant communication requirements that heavily depend on the network infrastructure. The inability to hide this particular AllReduce behind computation means it directly adds to the critical path of forward propagation.</p>
 
-        <p><img alt="Impact of Tensor Parallelism on model performance and batch size capacity: while increasing TP leads to reduced per-GPU throughput (left), it enables processing of larger batch sizes (right), illustrating the trade-off between computational efficiency and memory availability in distributed training." src="/assets/images/tp_scaling.svg" /></p>
+        <iframe class="l-body-outset" id="plotFrame13" src="assets/data/benchmarks/tp_scaling.html" width="90%" scrolling="no" frameborder="0"></iframe>
+        <script>
+            window.addEventListener('load', function() {
+                const frame = document.getElementById('plotFrame13');
+                frame.style.height = frame.contentWindow.document.documentElement.scrollHeight + 'px';
+                frame.style.width = frame.contentWindow.document.documentElement.scrollWidth + 'px';
+            });
+        </script>
+<!-- 
+        <p><img alt="Impact of Tensor Parallelism on model performance and batch size capacity: while increasing TP leads to reduced per-GPU throughput (left), it enables processing of larger batch sizes (right), illustrating the trade-off between computational efficiency and memory availability in distributed training." src="/assets/images/tp_scaling.svg" /></p> -->
 
         <p>Impact of Tensor Parallelism on model performance and batch size capacity: while increasing TP leads to reduced per-GPU throughput (left), it enables processing of larger batch sizes (right), illustrating the trade-off between computational efficiency and memory availability in distributed training.</p>
 
@@ -1262,7 +1271,6 @@
                 frame.style.width = frame.contentWindow.document.documentElement.scrollWidth + 'px';
             });
         </script>
-
         <!-- <p><img alt="pp_memoryusage.svg" src="/assets/images/pp_memoryusage.svg" /></p> -->
 
         <p>Looking at the figure above, we notice something interesting: while the parameters are nicely split across GPUs, the activation memory remains the same on each GPU! This is because each GPU still needs to process the full batch of data, just with different layers. The activations from one GPU's layers need to be sent to the next GPU to continue the forward pass.</p>
@@ -1395,7 +1403,6 @@
                 frame.style.width = frame.contentWindow.document.documentElement.scrollWidth + 'px';
             });
         </script>
-
         <!-- <p><img alt="pp_bubblesize.png" src="/assets/images/pp_bubblesize.png" /></p> -->
 
 

src/index.html

@@ -849,7 +849,7 @@
 
         <p>In practice a small example of the operation looks like this:</p>
 
-        <p><img alt="image.png" src="/assets/images/tp_diagram.png" /></p>
+        <p><img class"l-body" alt="TP diagram" src="/assets/images/tp_diagram.svg" /></p>
 
         <p>Let’s see how we can parallelise this operation! In tensor parallelism, tensors will be split into N shards along a particular dimension and distributed across N GPUs. Matrices can be split either on the column part or row part leading to row and column parallelism. One thing we’ll see in the following is that choosing row or column sharding will require different communications primitives.</p>
 
@@ -911,7 +911,16 @@
 
         <p>Tensor parallelism does help reduce activation memory for the matrix multiplications since the intermediate activations are sharded across GPUs. However, we still need to gather the full activations for operations like LayerNorm, which means we're not getting the full memory benefits we could. Additionally, it introduces significant communication requirements that heavily depend on the network infrastructure. The inability to hide this particular AllReduce behind computation means it directly adds to the critical path of forward propagation.</p>
 
-        <p><img alt="Impact of Tensor Parallelism on model performance and batch size capacity: while increasing TP leads to reduced per-GPU throughput (left), it enables processing of larger batch sizes (right), illustrating the trade-off between computational efficiency and memory availability in distributed training." src="/assets/images/tp_scaling.svg" /></p>
+        <iframe class="l-body-outset" id="plotFrame13" src="assets/data/benchmarks/tp_scaling.html" width="90%" scrolling="no" frameborder="0"></iframe>
+        <script>
+            window.addEventListener('load', function() {
+                const frame = document.getElementById('plotFrame13');
+                frame.style.height = frame.contentWindow.document.documentElement.scrollHeight + 'px';
+                frame.style.width = frame.contentWindow.document.documentElement.scrollWidth + 'px';
+            });
+        </script>
+<!-- 
+        <p><img alt="Impact of Tensor Parallelism on model performance and batch size capacity: while increasing TP leads to reduced per-GPU throughput (left), it enables processing of larger batch sizes (right), illustrating the trade-off between computational efficiency and memory availability in distributed training." src="/assets/images/tp_scaling.svg" /></p> -->
 
         <p>Impact of Tensor Parallelism on model performance and batch size capacity: while increasing TP leads to reduced per-GPU throughput (left), it enables processing of larger batch sizes (right), illustrating the trade-off between computational efficiency and memory availability in distributed training.</p>
 
@@ -1262,7 +1271,6 @@
                 frame.style.width = frame.contentWindow.document.documentElement.scrollWidth + 'px';
             });
         </script>
-
         <!-- <p><img alt="pp_memoryusage.svg" src="/assets/images/pp_memoryusage.svg" /></p> -->
 
         <p>Looking at the figure above, we notice something interesting: while the parameters are nicely split across GPUs, the activation memory remains the same on each GPU! This is because each GPU still needs to process the full batch of data, just with different layers. The activations from one GPU's layers need to be sent to the next GPU to continue the forward pass.</p>
@@ -1395,7 +1403,6 @@
                 frame.style.width = frame.contentWindow.document.documentElement.scrollWidth + 'px';
             });
         </script>
-
         <!-- <p><img alt="pp_bubblesize.png" src="/assets/images/pp_bubblesize.png" /></p> -->