chore: bump rust version and annotate/fix all clippy warnings (huggin…

…gface#1455)

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
```

benchmark/src/app.rs

@@ -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"),

launcher/src/main.rs

@@ -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")
             }

router/client/src/client.rs

@@ -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),

router/client/src/sharded_client.rs

@@ -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?;