fix(cuda+csm): P0 rtx-backend-cuda compile fix + P2 rtx-csm clippy cleanup (#9)

Co-authored-by: Omar Sobh <[email protected]>
Co-committed-by: Omar Sobh <[email protected]>

crates/models/rtx-csm/src/csm_fork.rs

@@ -923,6 +923,7 @@ impl Model {
 
         self.decoder.clear_kv_cache();
         let mut decoder_pos = 0;
+        #[allow(clippy::needless_range_loop)]
         for i in 1..self.config.audio_num_codebooks {
             let proj_h = curr_h.apply(&self.projection)?;
             let decoder_h = self.decoder.forward(&proj_h, decoder_pos)?;
@@ -1019,6 +1020,7 @@ impl Model {
         let mut curr_h = Tensor::cat(&[h, c0_embed], 1)?;
         self.decoder.clear_kv_cache();
         let mut decoder_pos = 0usize;
+        #[allow(clippy::needless_range_loop)]
         for i in 1..self.config.audio_num_codebooks {
             let proj_h = curr_h.apply(&self.projection)?;
             let decoder_h = self.decoder.forward(&proj_h, decoder_pos)?;
@@ -1054,6 +1056,7 @@ impl Model {
     /// respectively).
     ///
     /// Reference: Koel-TTS (NVIDIA, arXiv 2502.05236), `cfg_scale ∈ [1.5, 3.0]`.
+    #[allow(clippy::too_many_arguments)]
     pub fn generate_frame_cfg(
         &mut self,
         cond_tokens: &Tensor,