kv-cache : optimize KQ mask construction (#18842)

* kv-cache : optimize KQ mask construction

* cont : add explanation + improve

* cont : fix
This commit is contained in:
Georgi Gerganov
2026-01-17 15:42:42 +02:00
committed by GitHub
parent a89002f07b
commit 2fbde785bc
4 changed files with 250 additions and 109 deletions
-2
View File
@@ -257,8 +257,6 @@ private:
size_t size_k_bytes() const;
size_t size_v_bytes() const;
bool is_masked_swa(llama_pos p0, llama_pos p1) const;
ggml_tensor * build_rope_shift(
const llama_cparams & cparams,
ggml_context * ctx,