huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-25 20:12:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: bump rust version and annotate/fix all clippy warnings (#1455)

Browse Source 
This PR just bumps the latest rust version and makes clippy happy

```bash
cargo clippy --all -- -D warnings
#    Finished dev [unoptimized + debuginfo] target(s) in 0.10s
```
This commit is contained in:
drbh 2024-01-22 09:22:54 -05:00 committed by Karol Damaszke
parent 77afb882dc
commit 935ee00749
4 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
benchmark/src/app.rs
View File

@ -466,7 +466,7 @@ fn latency_paragraph<'a>(latency: &mut Vec<f64>, name: &'static str) -> Paragrap
let latency_percentiles = crate::utils::percentiles(latency, &[50, 90, 99]);
// Latency p50/p90/p99 texts
let colors = vec![Color::LightGreen, Color::LightYellow, Color::LightRed];
let colors = [Color::LightGreen, Color::LightYellow, Color::LightRed];
for (i, (name, value)) in latency_percentiles.iter().enumerate() {
let span = Line::from(vec![Span::styled(
format!("{name}: {value:.2} ms"),

2
launcher/src/main.rs
View File

@ -55,6 +55,8 @@ impl std::fmt::Display for Quantization {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
// To keep in track with `server`.
match self {
#[allow(deprecated)]
// Use `eetq` instead, which provides better latencies overall and is drop-in in most cases
Quantization::Bitsandbytes => {
write!(f, "bitsandbytes")
}

2
router/client/src/client.rs
View File

@ -365,7 +365,7 @@ pub struct DecodeTimings {
impl DecodeTimings {
fn new(concat_ns: Option<u64>, forward_ns: u64, decode_ns: u64, total_ns: u64) -> Self {
Self {
concat: concat_ns.map(|v| Duration::from_nanos(v)),
concat: concat_ns.map(Duration::from_nanos),
forward: Duration::from_nanos(forward_ns),
decode: Duration::from_nanos(decode_ns),
total: Duration::from_nanos(total_ns),

2
router/client/src/sharded_client.rs
View File

@ -130,6 +130,7 @@ impl ShardedClient {
.iter_mut()
.map(|client| Box::pin(client.prefill(batch.clone())))
.collect();
#[allow(clippy::type_complexity)]
let results: Result<Vec<(Vec<Generation>, Option<CachedBatch>, PrefillTimings)>> =
join_all(futures).await.into_iter().collect();
let mut results = results?;
@ -162,6 +163,7 @@ impl ShardedClient {
.iter_mut()
.map(|client| Box::pin(client.decode(batches.clone())))
.collect();
#[allow(clippy::type_complexity)]
let results: Result<Vec<(Vec<Generation>, Option<CachedBatch>, DecodeTimings)>> =
join_all(futures).await.into_iter().collect();
let mut results = results?;