support qwen2 running on ascend npu device (#7022)

Co-authored-by: 刁莹煜 <diaoyingyu1@hisilicon.com>
2025-06-18 02:24:10 +08:00
parent 10d60cd41b
commit a39d928782
9 changed files with 63 additions and 16 deletions
--- a/docs/backend/native_api.ipynb
+++ b/docs/backend/native_api.ipynb
@@ -51,6 +51,10 @@
    "server_process, port = launch_server_cmd(\n",
    "    \"python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct --host 0.0.0.0\"\n",
    ")\n",
+    "## To run qwen2.5-0.5b-instruct model on the Ascend-Npu, you can execute the following command:\n",
+    "# server_process, port = launch_server_cmd(\n",
+    "#     \"python3 -m sglang.launch_server --model-path qwen/qwen2.5-0.5b-instruct --host 0.0.0.0 --device npu --tp 2 --attention-backend torch_native\"\n",
+    "# )\n",
    "\n",
    "wait_for_server(f\"http://localhost:{port}\")"
   ]