mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-24 00:12:08 +00:00
parent
136fb7e9b9
commit
8980bf43d7
@ -147,7 +147,9 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
|
||||
tracing::info!("Downloading tokenizer");
|
||||
|
||||
// Parse Huggingface hub token
|
||||
let auth_token = std::env::var("HF_TOKEN").or_else(|_| std::env::var("HUGGING_FACE_HUB_TOKEN")).ok();
|
||||
let auth_token = std::env::var("HF_TOKEN")
|
||||
.or_else(|_| std::env::var("HUGGING_FACE_HUB_TOKEN"))
|
||||
.ok();
|
||||
|
||||
// Download and instantiate tokenizer
|
||||
// We need to download it outside of the Tokio runtime
|
||||
|
@ -766,7 +766,7 @@ fn num_cuda_devices() -> Option<usize> {
|
||||
Err(_) => match env::var("NVIDIA_VISIBLE_DEVICES") {
|
||||
Ok(devices) => devices,
|
||||
Err(_) => env::var("ZE_AFFINITY_MASK").ok()?,
|
||||
}
|
||||
},
|
||||
};
|
||||
let n_devices = devices.split(',').count();
|
||||
Some(n_devices)
|
||||
@ -1229,7 +1229,6 @@ fn spawn_webserver(
|
||||
router_args.push("--otlp-service-name".to_string());
|
||||
router_args.push(otlp_service_name);
|
||||
|
||||
|
||||
// CORS origins
|
||||
for origin in args.cors_allow_origin.into_iter() {
|
||||
router_args.push("--cors-allow-origin".to_string());
|
||||
|
@ -159,7 +159,9 @@ async fn main() -> Result<(), RouterError> {
|
||||
});
|
||||
|
||||
// Parse Huggingface hub token
|
||||
let authorization_token = std::env::var("HF_TOKEN").or_else(|_| std::env::var("HUGGING_FACE_HUB_TOKEN")).ok();
|
||||
let authorization_token = std::env::var("HF_TOKEN")
|
||||
.or_else(|_| std::env::var("HUGGING_FACE_HUB_TOKEN"))
|
||||
.ok();
|
||||
|
||||
// Tokenizer instance
|
||||
// This will only be used to validate payloads
|
||||
|
Loading…
Reference in New Issue
Block a user