sglangv0.5.2 & support Qwen3-Next-80B-A3B-Instruct

examples/frontend_language/usage/triton/Dockerfile

@@ -0,0 +1,10 @@
+FROM nvcr.io/nvidia/tritonserver:24.01-py3
+
+WORKDIR /opt
+
+RUN git clone https://github.com/sgl-project/sglang.git
+
+WORKDIR /opt/sglang
+RUN pip install --upgrade pip && \
+    pip install -e "python[all]" && \
+    pip install datasets

examples/frontend_language/usage/triton/README.md

@@ -0,0 +1,35 @@
+# sglang_triton
+
+Build the docker image:
+```
+docker build -t sglang-triton .
+```
+
+Then do:
+```
+docker run -ti --gpus=all --network=host --name sglang-triton -v ./models:/mnt/models sglang-triton
+```
+
+inside the docker container:
+```
+cd sglang
+python3 -m sglang.launch_server --model-path mistralai/Mistral-7B-Instruct-v0.2 --port 30000 --mem-fraction-static 0.9
+```
+
+with another shell, inside the docker container:
+```
+docker exec -ti sglang-triton /bin/bash
+cd /mnt
+tritonserver --model-repository=/mnt/models
+```
+
+
+Send request to the server:
+```
+curl -X POST http://localhost:8000/v2/models/character_generation/generate \
+-H "Content-Type: application/json" \
+-d '{
+  "INPUT_TEXT": ["harry"]
+}'
+
+```

examples/frontend_language/usage/triton/models/character_generation/config.pbtxt

@@ -0,0 +1,23 @@
+name: "character_generation"
+backend: "python"
+input [
+    {
+        name: "INPUT_TEXT"
+        data_type: TYPE_STRING
+        dims: [ -1 ]
+    }
+]
+output [
+    {
+        name: "OUTPUT_TEXT"
+        data_type: TYPE_STRING
+        dims: [ -1 ]
+    }
+]
+instance_group [
+    {
+        count: 1
+        kind: KIND_GPU
+        gpus: [ 0 ]
+    }
+]