huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-06-19 15:52:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

change env var names

Browse Source
This commit is contained in:
Philipp Schmid 2023-02-28 14:00:32 +01:00 committed by OlivierDehaene
parent ce09fd32a1
commit 7bea9a105e
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
launcher/src/main.rs
View File

@ -21,13 +21,13 @@ use subprocess::{ExitStatus, Popen, PopenConfig, PopenError, Redirection};
struct Args { struct Args {
#[clap(default_value = "bigscience/bloom-560m", long, env = "HF_MODEL_ID")] #[clap(default_value = "bigscience/bloom-560m", long, env = "HF_MODEL_ID")]
model_id: String, model_id: String,
#[clap(long, env)] #[clap(long, env = "HF_MODEL_REVISION")]
revision: Option<String>, revision: Option<String>,
#[clap(long, env)] #[clap(long, env)]
sharded: Option<bool>, sharded: Option<bool>,
#[clap(long, env = "SM_NUM_GPUS")] #[clap(long, env = "SM_NUM_GPUS")]
num_shard: Option<usize>, num_shard: Option<usize>,
#[clap(long, env)] #[clap(long, env = "HF_MODEL_QUANTIZE")]
quantize: bool, quantize: bool,
#[clap(default_value = "128", long, env)] #[clap(default_value = "128", long, env)]
max_concurrent_requests: usize, max_concurrent_requests: usize,