Small improvement of native api docs (#5139)

Co-authored-by: zhaochenyang20 <zhaochen20@outlook.com>
This commit is contained in:
simveit
2025-04-08 21:09:26 +02:00
committed by GitHub
parent 6d3b35fae9
commit f8194b267c

View File

@@ -371,7 +371,9 @@
"source": [
"## Capture expert selection distribution in MoE models\n",
"\n",
"SGLang Runtime supports recording the number of times an expert is selected in a MoE model run for each expert in the model. This is useful when analyzing the throughput of the model and plan for optimization."
"SGLang Runtime supports recording the number of times an expert is selected in a MoE model run for each expert in the model. This is useful when analyzing the throughput of the model and plan for optimization.\n",
"\n",
"*Note: We only print out the first 10 lines of the csv below for better readability. Please adjust accordingly if you want to analyze the results more deeply.*"
]
},
{
@@ -412,9 +414,13 @@
"\n",
"output_file = glob.glob(\"expert_distribution_*.csv\")[0]\n",
"with open(output_file, \"r\") as f:\n",
" print_highlight(\"Content of dumped record:\")\n",
" for line in f:\n",
" print_highlight(line.strip())"
" print_highlight(\"\\n| Layer ID | Expert ID | Count |\")\n",
" print_highlight(\"|----------|-----------|--------|\")\n",
" next(f)\n",
" for i, line in enumerate(f):\n",
" if i < 9:\n",
" layer_id, expert_id, count = line.strip().split(\",\")\n",
" print_highlight(f\"| {layer_id:8} | {expert_id:9} | {count:6} |\")"
]
},
{