mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
5460d18b10
* feat: trtllm-serve multimodal support Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * remove disable argument Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * remove disable Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * add and separate tests and move the doc Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> * remove block_resue arg from serve.py Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> --------- Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com> Co-authored-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
12 lines
381 B
Bash
12 lines
381 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
|
|
}'
|