mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-29 23:23:48 +08:00
f25c7cefb4
Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com> Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com> Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>
12 lines
379 B
Bash
12 lines
379 B
Bash
#! /usr/bin/env bash
|
|
|
|
curl http://localhost:8000/v1/chat/completions \
|
|
-H "Content-Type: application/json" \
|
|
-d '{
|
|
"model": TinyLlama-1.1B-Chat-v1.0,
|
|
"messages":[{"role": "system", "content": "You are a helpful assistant."},
|
|
{"role": "user", "content": "Where is New York?"}],
|
|
"max_tokens": 16,
|
|
"temperature": 0
|
|
}'
|