Skip to content

Add clear_kv_cache to quantized_llama and quantized_qwen2 #3536

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ivarflakstad merged 1 commit into from
May 16, 2026
Merged

Add clear_kv_cache to quantized_llama and quantized_qwen2 #3536

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions candle-transformers/src/models/quantized_llama.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -555,6 +555,16 @@ impl ModelWeights {
}
}

/// Clear the KV cache across all layers.
///
/// Call this between independent conversations to free cached attention
/// state without recreating the model.
pub fn clear_kv_cache(&mut self) {
for layer in self.layers.iter_mut() {
layer.kv_cache = None;
}
}

pub fn forward(&mut self, x: &Tensor, index_pos: usize) -> Result<Tensor> {
let (_b_sz, seq_len) = x.dims2()?;
let mask = if seq_len == 1 {
Expand Down
10 changes: 10 additions & 0 deletions candle-transformers/src/models/quantized_qwen2.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -304,6 +304,16 @@ impl ModelWeights {
}
}

/// Clear the KV cache across all layers.
///
/// Call this between independent conversations to free cached attention
/// state without recreating the model.
pub fn clear_kv_cache(&mut self) {
for layer in self.layers.iter_mut() {
layer.kv_cache = None;
}
}

pub fn forward(&mut self, x: &Tensor, index_pos: usize) -> Result<Tensor> {
let (_b_sz, seq_len) = x.dims2()?;
let mask = if seq_len == 1 {
Expand Down
Loading