Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

(launcher) default new server::run parameters to false for now

This commit is contained in:
Morgan Funtowicz 2024-07-31 09:06:52 +00:00
parent 8989c585c6
commit 31ebfd0dd7
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
backends/trtllm/src/main.rs
View File

@ -1,12 +1,10 @@
use clap::Parser;
use std::collections::HashMap; use std::collections::HashMap;
use std::path::PathBuf; use std::path::PathBuf;
use clap::Parser;
use tokenizers::{FromPretrainedParameters, Tokenizer};
use text_generation_backends_trtllm::errors::TensorRtLlmBackendError; use text_generation_backends_trtllm::errors::TensorRtLlmBackendError;
use text_generation_backends_trtllm::TensorRtLlmBackend; use text_generation_backends_trtllm::TensorRtLlmBackend;
use text_generation_router::server; use text_generation_router::server;
use tokenizers::{FromPretrainedParameters, Tokenizer};
/// App Configuration /// App Configuration
#[derive(Parser, Debug)] #[derive(Parser, Debug)]
@ -160,6 +158,8 @@ async fn main() -> Result<(), TensorRtLlmBackendError> {
messages_api_enabled, messages_api_enabled,
true, true,
max_client_batch_size, max_client_batch_size,
false,
false
) )
.await?; .await?;
Ok(()) Ok(())