gahow/xserv
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style: format Rust workspace

Browse Source
This commit is contained in:
Gahow Wang
2026-06-18 18:11:58 +08:00
parent 013465fc06
commit 531cd3fe08
57 changed files with 4045 additions and 1204 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
crates/xserv-model/src/sampling.rs
View File

@@ -11,7 +11,11 @@ pub struct SamplingParams {
impl Default for SamplingParams {
fn default() -> Self {
Self { temperature: 0.0, top_k: 0, top_p: 1.0 }
Self {
temperature: 0.0,
top_k: 0,
top_p: 1.0,
}
}
}
@@ -134,9 +138,14 @@ pub fn sample_greedy_penalized(logits: &Tensor, recent: &[u32], penalty: f32) ->
let seq_len = logits.shape()[0];
let logits_cpu = logits.to_device(Device::Cpu);
let mut last_row: Vec<f32> = match logits.dtype() {
DType::F32 => logits_cpu.as_slice::<f32>()[(seq_len - 1) * vocab_size..seq_len * vocab_size].to_vec(),
DType::BF16 => logits_cpu.as_slice::<bf16>()[(seq_len - 1) * vocab_size..seq_len * vocab_size]
.iter().map(|v| v.to_f32()).collect(),
DType::F32 => {
logits_cpu.as_slice::<f32>()[(seq_len - 1) * vocab_size..seq_len * vocab_size].to_vec()
}
DType::BF16 => logits_cpu.as_slice::<bf16>()
[(seq_len - 1) * vocab_size..seq_len * vocab_size]
.iter()
.map(|v| v.to_f32())
.collect(),
_ => panic!("unsupported dtype for sampling: {:?}", logits.dtype()),
};
if penalty > 1.0 {