mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
10 lines
239 B
Bash
10 lines
239 B
Bash
#! /usr/bin/env bash
|
|
|
|
curl http://localhost:8000/v1/responses \
|
|
-H "Content-Type: application/json" \
|
|
-d '{
|
|
"model": "TinyLlama-1.1B-Chat-v1.0",
|
|
"input": "Where is New York?",
|
|
"max_output_tokens": 16
|
|
}'
|